© 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. 2-GEMMASCOPE-RES-16K
    11. 4118
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to statistical and probabilistic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.52
     to
    -0.47
     on
    -0.47
     tervez
    -0.46
    ↵↵
    -0.45
     mise
    -0.43
     South
    -0.42
    сте
    -0.42
     line
    -0.41
     not
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    1.12
    TypedDataSet
    1.11
     виправивши
    1.10
     متعلقه
    1.09
     Roskov
    1.08
     tartalomajánló
    1.06
     resourceCulture
    0.99
    parsedMessage
    0.96
    postIndex
    0.93
     Мексичка
    0.91
    Activations Density 3.080%

    No Known Activations