© 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. 13713
    Prev
    Next
    INDEX
    Explanations

    patterns and relationships in technical or scientific data

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

    descriptive adjectives that characterize properties or qualities of objects, particularly in technical or analytical contexts.

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

    adjectives describing age, novelty, or recency (early, old, new, current, etc.).

    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
     archaeological
    -0.47
    ActionCreators
    -0.46
    RegressionTest
    -0.45
    findpost
    -0.45
    butterfly
    -0.45
     Chwiliwch
    -0.44
     politie
    -0.44
    ゅ
    -0.44
     alcoholic
    -0.43
     Educational
    -0.43
    POSITIVE LOGITS
     stuff
    0.84
     efforts
    0.65
     offerings
    0.63
     effort
    0.63
     arrangements
    0.61
    したもの
    0.61
    するもの
    0.61
     hacerlo
    0.59
    のもの
    0.57
     results
    0.56
    Activations Density 2.180%

    No Known Activations