© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    structure and descriptive features of places or communities

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

    descriptive listing content with multiple detailed amenities and features separated by commas or periods.

    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
    toHaveBeenCalled
    -0.36
     сравнению
    -0.35
     vs
    -0.31
    */].
    -0.31
    EndInit
    -0.31
     weakest
    -0.30
     ModelExpression
    -0.29
     desses
    -0.28
    おはようございます
    -0.28
     hingegen
    -0.28
    POSITIVE LOGITS
    featureID
    0.66
    Additional
    0.58
     Additional
    0.56
     Truly
    0.56
    Outdoor
    0.56
    Nearby
    0.54
    oredCriteria
    0.54
    Truly
    0.53
     Outdoor
    0.53
     nearby
    0.53
    Activations Density 0.040%

    No Known Activations