© 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. 10655
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate methods or strategies for accomplishing tasks

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

    the phrase "way to" followed by action verbs.

    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
     ModelExpression
    -0.40
    MathML
    -0.38
    CloseOperation
    -0.29
     craindre
    -0.28
     updatedAt
    -0.28
     Untersuchungen
    -0.28
     szczę
    -0.27
     fases
    -0.27
     Voraussetzungen
    -0.27
    декс
    -0.27
    POSITIVE LOGITS
    WithIOException
    0.66
     estekak
    0.66
     autorytatywna
    0.65
     Chwiliwch
    0.62
    expandindo
    0.60
    LookAnd
    0.59
    تقاوى
    0.58
     ways
    0.57
     بيها
    0.57
    новништво
    0.55
    Activations Density 0.153%

    No Known Activations