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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14915
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and opinions

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

    First-person narration

    np_acts-logits-general · gemini-2.0-flash

    personal experiences and opinions

    np_acts-logits-general · gemini-2.5-flash-lite

    first-person, autobiographical statements expressing personal experience, thoughts, or preferences within informal explanations or advice.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    
    -0.46
    glLoad
    -0.40
     representative
    -0.37
     Magaz
    -0.35
     resolution
    -0.35
    FirstResponder
    -0.34
    MethodManager
    -0.34
     پاس
    -0.33
     repres
    -0.33
    komna
    -0.33
    POSITIVE LOGITS
     propOrder
    0.70
    AutoScaleMode
    0.57
     mijne
    0.54
    كويكب
    0.50
     mío
    0.48
     >=",
    0.47
     <=",
    0.47
     argint
    0.47
     HasFactory
    0.47
     ausdrück
    0.47
    Activations Density 0.213%

    No Known Activations