© 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. 38768
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting characters used in code or text

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

    mathematical expressions and code delimiters

    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
     informée
    -0.43
    Портал
    -0.40
    /******/
    -0.35
     adopté
    -0.34
     UIColor
    -0.34
     adota
    -0.33
     assunto
    -0.32
     erfahren
    -0.32
    Shared
    -0.32
    rahat
    -0.31
    POSITIVE LOGITS
    SequentialGroup
    0.65
    NamedQueries
    0.61
     HttpNotFound
    0.60
     kasarigan
    0.59
    ViewImports
    0.57
    queryInterface
    0.54
    Rüyada
    0.53
     disambiguazione
    0.52
    GEBURTSDATUM
    0.51
    Vidite
    0.51
    Activations Density 0.000%

    No Known Activations