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. 9-GEMMASCOPE-RES-16K
    6. 3149
    Prev
    Next
    INDEX
    Explanations

    references to physical measurements or specifications, particularly related to thickness

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

    an object's thickness

    np_acts-logits-general · gemini-2.0-flash

    thickness

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    astéroïdes
    -0.78
    ⟬
    -0.77
    ロウィン
    -0.73
    LLocation
    -0.73
    SequentialGroup
    -0.71
    ConstraintMaker
    -0.69
    aarrggbb
    -0.68
    endphp
    -0.67
    HostException
    -0.66
    iſchen
    -0.66
    POSITIVE LOGITS
     thick
    1.76
    Thick
    1.56
     Thick
    1.55
     thickness
    1.52
     thicker
    1.50
    thick
    1.50
    Thickness
    1.45
    thickness
    1.36
     Thickness
    1.35
     thin
    1.27
    Activations Density 0.211%

    No Known Activations