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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9593
    Prev
    Next
    INDEX
    Explanations

    the beginning of the text or sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     postIndex
    -0.55
    WaitGroup
    -0.47
    URLException
    -0.47
    geld
    -0.46
     ob
    -0.46
    anneer
    -0.45
    CardBody
    -0.45
    mongoose
    -0.45
    string
    -0.43
    Ob
    -0.43
    POSITIVE LOGITS
     avoient
    0.80
     ProtoMessage
    0.79
     RIPRODUZIONE
    0.79
     auroit
    0.78
     الاطلاع
    0.78
     vôtre
    0.77
     faveur
    0.76
     feroit
    0.75
     nôtre
    0.73
    CloseOperation
    0.73
    Activations Density 0.097%

    No Known Activations