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. 103549
    Prev
    Next
    INDEX
    Explanations

    specific symbols and punctuation used in coding syntax and programming languages

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

    programming keywords

    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
     للاسماء
    -0.65
    WebElementEntity
    -0.55
     snippetHide
    -0.54
     שוליים
    -0.54
     المعيارى
    -0.53
    VIAF
    -0.51
    Билгалдахарш
    -0.50
    Personendaten
    -0.48
    مصادر
    -0.48
    లాలు
    -0.47
    POSITIVE LOGITS
     fotográfico
    0.41
     seragam
    0.40
     Flüs
    0.37
     tangan
    0.37
     alambre
    0.37
     hidráulica
    0.36
     artesanales
    0.36
     bruja
    0.36
     estratégica
    0.36
     celebridades
    0.36
    Activations Density 0.091%

    No Known Activations