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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 891
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structures

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

    numeric literals and mathematical/technical operations in code and technical documentation.

    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
     BorderSide
    -0.48
     protoimpl
    -0.46
    fillType
    -0.46
    AsUp
    -0.45
    ValueStyle
    -0.42
    ChildScrollView
    -0.42
    ImageContext
    -0.41
    CppMethod
    -0.40
     disambiguazione
    -0.39
    الحياه
    -0.39
    POSITIVE LOGITS
    Maryland
    0.50
     Maryland
    0.50
     svg
    0.48
     Kepler
    0.44
    IconModule
    0.44
     SVG
    0.43
    flink
    0.43
     pungkas
    0.43
     Orioles
    0.43
    SVG
    0.42
    Activations Density 0.208%

    No Known Activations