© 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. 20-GEMMASCOPE-RES-16K
    11. 5245
    Prev
    Next
    INDEX
    Explanations

    specific coding functions and methods related to user interface interactions

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

    low-level programming code, specifically related to embedded systems and technical configurations.

    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
     ་་
    -0.83
     ſind
    -0.67
    httphttps
    -0.59
    SequentialGroup
    -0.57
     ―――――
    -0.56
     $_(
    -0.56
     ſich
    -0.55
    󠁢
    -0.55
     ddelwed
    -0.55
     miniaturka
    -0.55
    POSITIVE LOGITS
     ویکی‌پدی
    0.51
     CanadaChoose
    0.47
     Италијани
    0.38
     tartalomajánló
    0.36
    MessageOf
    0.33
    KURZBESCHREIBUNG
    0.32
     Савезне
    0.31
     مشارکت‌کنندگان
    0.30
     Walkover
    0.30
    expandindo
    0.30
    Activations Density 37.834%

    No Known Activations