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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2063
    Prev
    Next
    INDEX
    Explanations

    data or statistical information relevant to historical events or categories

    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
    )++;
    -0.48
     redan
    -0.46
    анти
    -0.45
     henvisninger
    -0.45
    sieht
    -0.44
     '.';
    -0.44
     Riverside
    -0.43
    будь
    -0.42
    外部リンク
    -0.42
    matan
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.70
    uxxxx
    0.69
    NameInMap
    0.69
    OGND
    0.68
    ViewFeatures
    0.63
    UnsafeEnabled
    0.63
     Demp
    0.63
     newBuilder
    0.60
    astify
    0.60
    elemField
    0.60
    Activations Density 0.138%

    No Known Activations