© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 121739
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and concepts related to algebraic structures and functions

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

    potty training or technical compilation

    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
    KommentareTeilen
    -0.52
     drawdown
    -0.43
    highlights
    -0.43
     highlights
    -0.41
    Highlights
    -0.41
    highlight
    -0.39
    ens
    -0.39
     Highlights
    -0.39
     allocations
    -0.39
     dealings
    -0.39
    POSITIVE LOGITS
     tự
    2.59
    ự
    1.48
    Ự
    0.91
     Natural
    0.74
     natural
    0.73
    自然
    0.72
    Natural
    0.71
     자
    0.71
    AUTO
    0.69
     tụ
    0.68
    Activations Density 0.001%

    No Known Activations