© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14991
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and identifiers typically used in scientific contexts, especially related to proteins and genes.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    textual gibberish or nonsensical patterns.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    genetic mutation nomenclature, particularly focusing on amino acid changes and their positions within proteins.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Genetic mutations/variations

    np_acts-logits-general · gemini-2.0-flash

    protein mutation annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.59
     оригіналу
    -0.58
    tagHelperRunner
    -0.55
    WebElementEntity
    -0.54
    DockStyle
    -0.54
     Pliocene
    -0.53
     برانيه
    -0.53
    PreferredItem
    -0.53
    DoubleQuotes
    -0.52
    StoryboardSegue
    -0.52
    POSITIVE LOGITS
    ########.
    0.75
    სქოლიო
    0.54
    HomeAsUpEnabled
    0.50
    ONYMOUS
    0.48
    FunctionFlags
    0.46
    pere
    0.46
     Forman
    0.46
     cast
    0.45
    цтва
    0.45
    Preced
    0.44
    Activations Density 0.444%

    No Known Activations