© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38611
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of sentences or new sections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.84
    endpush
    -0.79
    AccessorTable
    -0.79
     vPvB
    -0.79
    المكان
    -0.75
     nakalista
    -0.74
    :+:
    -0.73
    rsiniz
    -0.72
    +#+
    -0.71
    cerpt
    -0.68
    POSITIVE LOGITS
    featureID
    0.53
    oubliez
    0.52
     the
    0.52
    wel
    0.51
     cuenta
    0.50
     Cuenta
    0.50
    Cud
    0.49
    ฏิ
    0.49
    findpost
    0.48
    )$_
    0.48
    Activations Density 0.005%

    No Known Activations