© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to statistical methods and measurements

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

    peak physiological parameters like absolute values

    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
    TestingModule
    -0.55
     оригіналу
    -0.46
    MLLoader
    -0.46
     sche
    -0.44
    StoryboardSegue
    -0.43
     AttributeSet
    -0.42
     sw
    -0.41
    Pä
    -0.40
    hdas
    -0.40
    ন্দ
    -0.39
    POSITIVE LOGITS
    potranspiration
    0.64
     measurement
    0.61
     rate
    0.54
     eficiencia
    0.52
     taux
    0.51
     tasa
    0.51
    ความ
    0.51
     desempenho
    0.50
     measurements
    0.50
     ganancias
    0.49
    Activations Density 0.524%

    No Known Activations