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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 14368
    Prev
    Next
    INDEX
    Explanations

    numeric values and their configurations in data representations

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

    zero followed by closing bracket

    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
     the
    -0.50
    ệp
    -0.39
    rapper
    -0.39
     Schreiber
    -0.39
     adaptation
    -0.38
    ➟
    -0.38
    \":\"
    -0.38
    adapted
    -0.37
     QtWidgets
    -0.37
     dien
    -0.37
    POSITIVE LOGITS
    0
    0.83
     zero
    0.63
    DockStyle
    0.60
    0
    0.60
     Zero
    0.56
    zero
    0.55
    Zero
    0.55
    zeros
    0.52
     ZERO
    0.52
    RectangleBorder
    0.51
    Activations Density 0.257%

    No Known Activations