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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4166
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to mechanical and electric machinery

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

    patterns of historical change or developments occurring over specific time periods.

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

    words related to historical time periods and technological or industrial development.

    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
    évaluateur
    -0.54
     årets
    -0.50
    ölf
    -0.48
     miesię
    -0.47
    adaptiveStyles
    -0.46
     Months
    -0.45
     jöv
    -0.45
     ſind
    -0.44
    FormTagHelper
    -0.44
     davidson
    -0.42
    POSITIVE LOGITS
     década
    1.27
     دهه
    1.16
     during
    1.11
     decades
    1.10
     early
    1.08
     late
    1.05
     décadas
    1.02
     decade
    1.00
    during
    0.99
     circa
    0.96
    Activations Density 0.969%

    No Known Activations