© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    structured data or elements related to forms and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nicknames
    -0.88
     Titles
    -0.77
     titles
    -0.77
     filenames
    -0.77
     betweenstory
    -0.73
    Titles
    -0.71
     surnames
    -0.70
    titles
    -0.69
     usernames
    -0.69
    CppMethod
    -0.68
    POSITIVE LOGITS
    name
    0.89
     name
    0.88
    Name
    0.69
    ame
    0.67
    名
    0.66
     na
    0.61
     nam
    0.58
     Nam
    0.54
     NA
    0.53
    nam
    0.52
    Activations Density 0.300%

    No Known Activations