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. 12-GEMMASCOPE-RES-16K
    6. 9733
    Prev
    Next
    INDEX
    Explanations

    constructions indicating evaluation or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.92
     myſelf
    -0.83
    writeFieldEnd
    -0.80
     defStyle
    -0.74
     <>",
    -0.74
    genheim
    -0.72
    DeleteBehavior
    -0.71
    évaluateur
    -0.70
    ACTERS
    -0.70
    ंदीखरीदारी
    -0.69
    POSITIVE LOGITS
     nevertheless
    0.60
     nonetheless
    0.57
     anyway
    0.50
    addGap
    0.47
    ah
    0.46
     hey
    0.44
    Izvori
    0.43
    hi
    0.42
    Sta
    0.41
    delig
    0.41
    Activations Density 0.265%

    No Known Activations