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. 16-GEMMASCOPE-RES-16K
    6. 6262
    Prev
    Next
    INDEX
    Explanations

    distinct stages of development in biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    พาะ
    -0.47
     manhã
    -0.46
     Danzig
    -0.44
     presence
    -0.43
    verse
    -0.42
    amycin
    -0.41
    acuzzi
    -0.41
    Erich
    -0.41
     Chambre
    -0.41
    lié
    -0.41
    POSITIVE LOGITS
     stages
    1.22
     Stages
    1.08
     stage
    1.05
    stages
    1.04
     STAGE
    1.03
    Stages
    1.00
     phases
    0.95
    Stage
    0.91
     Stage
    0.91
    stage
    0.91
    Activations Density 0.240%

    No Known Activations