Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 356
    Prev
    Next
    INDEX
    Explanations

    references to singular entities or consolidations into a single unit

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

    technical or legal language involving multiple components combined into a single unit or process.

    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
     βά
    -0.35
    guantes
    -0.35
     انتظار
    -0.33
    ber
    -0.32
    ref
    -0.31
    品
    -0.31
     значит
    -0.31
    chen
    -0.31
    match
    -0.31
     مناس
    -0.31
    POSITIVE LOGITS
     unified
    0.86
     unifying
    0.77
    Unified
    0.77
     Unified
    0.73
    unified
    0.70
     gemens
    0.66
    Tikang
    0.65
    oneofs
    0.63
     unify
    0.63
    统一
    0.59
    Activations Density 0.371%

    No Known Activations