Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2189
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilités
    -0.60
    findpost
    -0.55
    resizingMask
    -0.54
    </h5>
    -0.52
    +#+
    -0.52
    stdc
    -0.52
    Gambas
    -0.52
     يتيمه
    -0.51
    "
    
    -0.50
    Bibliograf
    -0.50
    POSITIVE LOGITS
    see
    0.74
    Figure
    0.68
    buttonBar
    0.65
    Table
    0.65
    例えば
    0.64
    ~.
    0.59
    Fig
    0.59
    orsese
    0.58
    %).
    0.57
    siehe
    0.57
    Activations Density 0.804%

    No Known Activations