© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 198
    Prev
    Next
    INDEX
    Explanations

    expressions related to strong opinions or critiques

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

    words and phrases expressing strong enthusiasm or intense emotion, particularly "rave" and variations like "raved" or "raving".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @dribnet

    rave reviewsroving yarn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.50
     виправивши
    -0.49
    AsUp
    -0.47
     INA
    -0.42
     DCT
    -0.42
     Serif
    -0.42
    bookId
    -0.42
     betweenstory
    -0.41
     employe
    -0.41
    ubro
    -0.41
    POSITIVE LOGITS
     rave
    1.70
     Rave
    1.47
     raving
    1.45
    rave
    1.23
     raging
    0.76
     hvě
    0.64
     hebat
    0.63
     paixão
    0.63
     sereia
    0.62
     głoś
    0.61
    Activations Density 0.003%

    No Known Activations