© 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. 12-GEMMASCOPE-RES-16K
    11. 3147
    Prev
    Next
    INDEX
    Explanations

    data type declarations, particularly involving character arrays and pointers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.57
     kepad
    -0.44
     fundación
    -0.43
     Menschheit
    -0.42
     Erwä
    -0.42
     tertentu
    -0.41
    zbęd
    -0.41
     McE
    -0.41
    webElementXpaths
    -0.41
     Begegn
    -0.40
    POSITIVE LOGITS
     char
    1.66
    char
    1.52
    Char
    1.22
     Char
    1.20
    CHAR
    1.20
     CHAR
    1.10
     chars
    1.02
     Charley
    0.85
    chars
    0.85
     Chara
    0.82
    Activations Density 0.185%

    No Known Activations