© 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. 36-GEMMASCOPE-RES-16K
    6. 7871
    Prev
    Next
    INDEX
    Explanations

    code-related elements that indicate labels and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.64
    ChildScrollView
    -0.55
    AddHtmlAttribute
    -0.50
    twimg
    -0.50
    Irak
    -0.49
    AER
    -0.49
    Oasis
    -0.48
    Arti
    -0.47
    Exo
    -0.47
    opp
    -0.46
    POSITIVE LOGITS
    épaisseur
    0.93
    enfance
    0.82
    échelle
    0.82
    écart
    0.76
    entraînement
    0.74
    échange
    0.74
    extrémité
    0.72
    équilibre
    0.71
    élaboration
    0.69
    hygiène
    0.69
    Activations Density 0.633%

    No Known Activations