© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7865
    Prev
    Next
    INDEX
    Explanations

    common phrases and patterns related to societal issues and occurrences

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

    statements asserting that something is a common or frequent occurrence.

    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
     utafitiHapana
    -0.56
     Comprometido
    -0.55
     Italijanski
    -0.53
    endpush
    -0.53
    ⤹
    -0.52
    DIPSETTING
    -0.51
    Gambas
    -0.50
     GenerationType
    -0.50
    __':
    -0.50
     ModelExpression
    -0.49
    POSITIVE LOGITS
     common
    1.64
     commonplace
    1.59
     normal
    1.56
     typical
    1.55
    common
    1.41
    normal
    1.30
     comum
    1.27
     usual
    1.24
    typical
    1.23
     comuns
    1.20
    Activations Density 0.632%

    No Known Activations