© 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. 38-GEMMASCOPE-RES-16K
    6. 7134
    Prev
    Next
    INDEX
    Explanations

    terms related to consistency and association in research or data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toHaveBeen
    -0.44
     wzglę
    -0.43
    tableCell
    -0.42
     userEmail
    -0.42
    stateMutability
    -0.41
     hemd
    -0.40
    ニーズ
    -0.40
    الإنجليزية
    -0.38
    vénients
    -0.38
     tubercle
    -0.38
    POSITIVE LOGITS
    fjspx
    0.59
    IntoConstraints
    0.54
    tagHelperRunner
    0.48
     primarily
    0.47
     defaultstate
    0.45
     solely
    0.45
    Билгалдахарш
    0.43
     initComponents
    0.43
     therewith
    0.42
    omeness
    0.42
    Activations Density 1.164%

    No Known Activations