Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11184
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly those related to formal proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.77
    TestingModule
    -0.71
    aarrggbb
    -0.69
    ConstraintMaker
    -0.68
    AddTagHelper
    -0.66
     saites
    -0.60
     للاسماء
    -0.59
    ViewFeatures
    -0.58
     invokingState
    -0.58
     OFDb
    -0.57
    POSITIVE LOGITS
     earlier
    0.32
     different
    0.31
    …~
    0.29
     ögon
    0.28
     Reforma
    0.28
     maupun
    0.28
     Augen
    0.28
     duomen
    0.28
    ształ
    0.27
     ausser
    0.27
    Activations Density 1.157%

    No Known Activations