© 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. 39662
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding structure or definitions

    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
    ())));
    -0.62
    __]
    -0.62
    '])->
    -0.59
    [])
    -0.58
    ='')
    -0.58
     Carré
    -0.57
    []]
    -0.55
     lo
    -0.54
    DBNull
    -0.54
     Lo
    -0.53
    POSITIVE LOGITS
    mybatisplus
    0.80
    makeConstraints
    0.76
    BufferException
    0.71
    ViewFeatures
    0.65
    LLocation
    0.64
     numberWith
    0.64
    tagHelperRunner
    0.63
    ConstraintMaker
    0.62
     cherchés
    0.59
     onCancelled
    0.59
    Activations Density 0.013%

    No Known Activations