© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    หน้านี้
    -0.43
    angliski
    -0.40
    ScopeManager
    -0.40
    IFORNIA
    -0.38
     canais
    -0.37
     contatto
    -0.36
     channels
    -0.36
    OOTDTY
    -0.36
    oa̍t
    -0.35
    uscitation
    -0.34
    POSITIVE LOGITS
     propOrder
    3.08
     العنوان
    0.71
     disambiguazione
    0.59
     Référence
    0.54
     ब्रेकडाउन
    0.53
     autorytatywna
    0.51
    eqref
    0.50
    hilt
    0.49
    GenerationType
    0.48
     NSCoder
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.