© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of being significant or noteworthy, often in relation to roles or characteristics

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

    phrases starting with "as a" in various contexts like legal, scientific, or descriptive statements.

    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
     Bupati
    -0.42
     politiet
    -0.40
     skolen
    -0.38
     undersø
    -0.38
     syke
    -0.37
     findes
    -0.36
     kirja
    -0.36
     rahasia
    -0.36
     Landkreis
    -0.36
    tidaknya
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.74
     Sebagai
    0.73
     ως
    0.73
     sebagai
    0.73
    sebagai
    0.71
    作为
    0.69
    作为一个
    0.69
    作為
    0.69
     Jako
    0.65
     فريبيس
    0.64
    Activations Density 0.167%

    No Known Activations