© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5949
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and scheduling tasks

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

    technical computing tasks involving cron jobs, scripting, and automated system processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.31
    endmodule
    -0.30
     ANSI
    -0.26
     lateinit
    -0.26
     addSubview
    -0.26
    ieR
    -0.25
     cận
    -0.25
    ⎩
    -0.25
    AnchorStyles
    -0.24
    aptation
    -0.23
    POSITIVE LOGITS
    queryInterface
    0.66
    SpringRunner
    0.65
     ویکی‌پدی
    0.63
    ImageContext
    0.58
    IndentedString
    0.57
     igång
    0.57
    enumii
    0.55
    UrlResolution
    0.55
     BATCH
    0.55
     processing
    0.53
    Activations Density 0.263%

    No Known Activations