© 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. 57616
    Prev
    Next
    INDEX
    Explanations

    punctuation or formatting markers in a coding context

    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
     كومونز
    -0.91
     myſelf
    -0.91
     PWN
    -0.91
     roulant
    -0.81
    bootstrapcdn
    -0.80
     Efq
    -0.79
    دانشنامهٔ
    -0.79
    )+"
    -0.79
     ſame
    -0.79
     laun
    -0.77
    POSITIVE LOGITS
     :
    0.99
     Humphries
    0.96
    ::::::::
    0.91
    いる
    0.89
    sertation
    0.87
    iwa
    0.86
     Rosenthal
    0.85
    허
    0.85
     Ayres
    0.83
    出版年
    0.80
    Activations Density 0.024%

    No Known Activations