© 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. 28-GEMMASCOPE-RES-16K
    11. 8202
    Prev
    Next
    INDEX
    Explanations

    code segments that reference intent handling and URI parsing in programming contexts

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    string literals or specific legal citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.59
    <?>>
    -0.55
    
    -0.54
     nonUne
    -0.52
    :✨
    -0.52
     contextLoads
    -0.52
    OCCURRED
    -0.52
    ArrowToggle
    -0.51
     {}),
    -0.51
     tartalomajánló
    -0.50
    POSITIVE LOGITS
     string
    0.91
     String
    0.80
    String
    0.80
     strings
    0.77
    NSString
    0.74
     str
    0.74
    string
    0.73
    字符串
    0.69
    getString
    0.69
    str
    0.69
    Activations Density 0.755%

    No Known Activations