© 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. 5190
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating expectations or assessments of one's situation

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

    comparative statements using "than" with pronouns like "they", "he", "I".

    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
    msgTypes
    -0.58
    styleType
    -0.53
    :✨
    -0.53
    تفصیلات
    -0.52
    RectangleBorder
    -0.52
    yarnpkg
    -0.50
    évaluateur
    -0.50
    gonic
    -0.49
     työn
    -0.48
     Ceramby
    -0.48
    POSITIVE LOGITS
    gtest
    0.34
     than
    0.34
    Cordialement
    0.33
     actuel
    0.33
     possible
    0.32
    它们
    0.32
     currently
    0.32
    它們
    0.32
     typelib
    0.32
     alcal
    0.31
    Activations Density 0.150%

    No Known Activations