© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 81929
    Prev
    Next
    INDEX
    Explanations

    tables and data structuring elements

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

    punctuation and table separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    enterOuterAlt
    -0.53
    PreInfinity
    -0.50
    MessageState
    -0.50
     autorytatywna
    -0.49
    ModelForm
    -0.48
     cherchés
    -0.48
    mbggenerated
    -0.46
    oredCriteria
    -0.45
     MatDialog
    -0.45
    abstractmethod
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.45
     שוליים
    0.41
    peteer
    0.39
    
    0.39
    etc
    0.38
    ...}
    0.38
    estinations
    0.38
     opio
    0.37
    rbrakk
    0.37
     etc
    0.36
    Activations Density 0.006%

    No Known Activations