© 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 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. 15083
    Prev
    Next
    INDEX
    Explanations

    elements related to participants or themes in artistic and social contexts

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

    phrases where "any" precedes nouns or noun phrases that describe categories, groups, or types of things.

    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
    featureID
    -0.59
     algunas
    -0.52
     sometimes
    -0.52
     שוליים
    -0.51
     invokingState
    -0.50
    sometimes
    -0.50
     algunos
    -0.49
     algumas
    -0.48
     resourceCulture
    -0.48
    Šaltiniai
    -0.47
    POSITIVE LOGITS
     whatsoever
    1.28
     imaginable
    0.97
     anywhere
    0.85
     anything
    0.83
     ANYTHING
    0.82
    anything
    0.80
     apapun
    0.77
     Anything
    0.77
    Anything
    0.75
     conceivable
    0.75
    Activations Density 0.395%

    No Known Activations