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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 829
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords relevant to APIs and programming structures.

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

    API-related code, including mentions of errors and responses.

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

    programming language keywords, identifiers, and syntax related to APIs and network protocols, particularly in C/C++ and mobile development contexts.

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

    Code or identifiers containing uppercase letters

    np_acts-logits-general · gemini-2.0-flash

    IS followed by underscore

    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
    featureID
    -0.85
    DeleteBehavior
    -0.77
    GEBURTSDATUM
    -0.68
    TagMode
    -0.68
    istoitu
    -0.66
    verwijspagina
    -0.65
    帖最后由
    -0.64
    ForValue
    -0.62
    GIVEREF
    -0.60
    LayoutConstraint
    -0.59
    POSITIVE LOGITS
     Diſ
    0.80
     pleaſure
    0.75
     reaſon
    0.73
     ſtate
    0.70
    <bos>
    0.67
     cauſe
    0.67
     Reſ
    0.67
     reafon
    0.66
     greateſt
    0.65
     Chriſt
    0.64
    Activations Density 0.748%

    No Known Activations