© 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. 78034
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to Lévy processes and statistical methods

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

    Lévy-Khintchine formula and approximants

    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
     concepto
    -0.40
     ORDERED
    -0.34
    WithIdentifier
    -0.34
     non
    -0.33
     Бере
    -0.33
     marche
    -0.32
     renda
    -0.32
     hierarchy
    -0.32
     ordering
    -0.32
     adaptation
    -0.32
    POSITIVE LOGITS
    AsUp
    0.85
    tvguidetime
    0.65
    ]")]
    0.61
     SEDS
    0.59
    berdayakan
    0.58
     Administrativna
    0.57
     AssemblyCulture
    0.56
     OMITBAD
    0.56
    ſelf
    0.56
    webElementXpaths
    0.56
    Activations Density 0.323%

    No Known Activations