Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 14008
    Prev
    Next
    INDEX
    Explanations

    occurrences of the '@@' token in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.77
     colgantes
    -0.63
     مصرى
    -0.63
    Carthy
    -0.63
    AsUp
    -0.61
    衛門
    -0.59
     cromado
    -0.59
    ragan
    -0.58
    ABULARY
    -0.58
    bootstrapcdn
    -0.57
    POSITIVE LOGITS
     виправивши
    0.78
    BeginContext
    0.72
    \{\\
    0.68
     يتيمه
    0.64
    SuppressLint
    0.64
    jspx
    0.60
    migrationBuilder
    0.54
     للاسماء
    0.51
     textStatus
    0.50
     Patt
    0.50
    Activations Density 0.004%

    No Known Activations