© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2298
    Prev
    Next
    INDEX
    Explanations

    coding syntax related to function definitions and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    assignment operators and variable declarations in source code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     podjela
    -0.51
     productividad
    -0.49
     escuchado
    -0.49
     vacunación
    -0.45
     miró
    -0.44
     hábiles
    -0.44
     electricidad
    -0.43
     sorpresas
    -0.42
     Lainnya
    -0.42
     comprometido
    -0.42
    POSITIVE LOGITS
     My
    0.56
     Energy
    0.56
     Peer
    0.54
     Advanced
    0.54
     Food
    0.53
     Base
    0.52
     Foot
    0.52
     Fuel
    0.51
     Bath
    0.51
     Car
    0.51
    Activations Density 0.463%

    No Known Activations