© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4837
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements and punctuation in programming or markup code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apuestas
    -0.27
     canales
    -0.25
     violencia
    -0.24
     violência
    -0.24
     זאת
    -0.24
     للاسماء
    -0.23
    illo
    -0.23
    лго
    -0.23
    /
    -0.23
    __(/*!
    -0.22
    POSITIVE LOGITS
    httphttps
    0.89
     CreateTagHelper
    0.82
    reportWebVitals
    0.75
    fjspx
    0.75
     ProtoMessage
    0.75
    WebVitals
    0.73
     snippetHide
    0.72
    WriteBarrier
    0.71
    UrlResolution
    0.71
    :✨
    0.70
    Activations Density 0.502%

    No Known Activations