© 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. 731
    Prev
    Next
    INDEX
    Explanations

    terms related to valuable American muscle cars

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

    details and statistics related to vintage American muscle cars, particularly the Plymouth Hemi 'Cuda.

    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
     lass
    -0.35
     Hy
    -0.35
    IContainer
    -0.35
     userInfo
    -0.35
    ьаж
    -0.35
     sacco
    -0.35
     SwitchCompat
    -0.33
     tartalomajánló
    -0.32
     op
    -0.32
    提
    -0.32
    POSITIVE LOGITS
     rarest
    0.77
     collectors
    0.70
     rare
    0.68
    webElementGuid
    0.68
     rarer
    0.67
     collector
    0.65
     collectible
    0.63
     rarity
    0.62
     Collectors
    0.60
     RARE
    0.60
    Activations Density 0.068%

    No Known Activations