© 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. 24-GEMMASCOPE-RES-16K
    11. 1281
    Prev
    Next
    INDEX
    Explanations

    elements related to programming, data processing, and statistical analysis

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

    Mathematical/statistical symbols and formulas

    np_acts-logits-general · gemini-2.0-flash

    likewise also too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.47
     Bulk
    -0.45
    دانشنامهٔ
    -0.43
     geslacht
    -0.42
    évaluateur
    -0.40
     Bottom
    -0.40
     سنت
    -0.40
     Others
    -0.39
    ErrUnexpectedEOF
    -0.39
    wardship
    -0.39
    POSITIVE LOGITS
    setVerticalGroup
    0.84
     likewise
    0.64
     też
    0.63
    nocześnie
    0.57
     también
    0.57
     tiež
    0.56
     ebenfalls
    0.56
     också
    0.55
     tampoco
    0.53
     także
    0.52
    Activations Density 1.185%

    No Known Activations