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. 34-GEMMASCOPE-RES-16K
    6. 11683
    Prev
    Next
    INDEX
    Explanations

    declarations of public methods and properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [
    -0.36
    to
    -0.35
     ért
    -0.35
    as
    -0.35
    io
    -0.33
    ies
    -0.32
    one
    -0.32
    or
    -0.31
    of
    -0.31
    amélioration
    -0.31
    POSITIVE LOGITS
     void
    0.84
     static
    0.76
    BibitemShut
    0.71
    XmlAccessorType
    0.69
    bibfield
    0.68
     enum
    0.68
     synchronized
    0.67
     CreateTagHelper
    0.66
    Tikang
    0.66
     AssemblyCulture
    0.65
    Activations Density 0.039%

    No Known Activations