© 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. 7472
    Prev
    Next
    INDEX
    Explanations

    terminology related to algorithms and data processing in scientific contexts

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

    phrases indicating capability or enabling action, often detecting when subjects "are able to" or "can" perform actions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words and phrases that describe comparative performance metrics and capabilities.

    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
    хьтан
    -0.50
    CloseOperation
    -0.47
    contentLoaded
    -0.47
    ########.
    -0.47
    MigrationBuilder
    -0.46
     queſta
    -0.44
    colhead
    -0.43
    featureID
    -0.42
    genodigd
    -0.40
     prí
    -0.40
    POSITIVE LOGITS
     processing
    0.75
    处理
    0.72
     handling
    0.71
    處理
    0.70
     처리
    0.68
    Handling
    0.66
     processed
    0.65
     handled
    0.65
     Handling
    0.63
    処理
    0.63
    Activations Density 1.789%

    No Known Activations