Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64685
    Prev
    Next
    INDEX
    Explanations

    terms related to gene expression in various cell types

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

    expressed in biological tissues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.56
    RenderAtEndOf
    -0.56
    AndEndTag
    -0.55
    httphttps
    -0.55
     betweenstory
    -0.52
    出版年
    -0.50
     chré
    -0.46
    HtmlAttribute
    -0.45
    setVerticalGroup
    -0.44
     مرئيه
    -0.44
    POSITIVE LOGITS
     tissues
    0.51
     testis
    0.48
    angerschaft
    0.46
     contexts
    0.41
     neurons
    0.40
    MigrationBuilder
    0.39
     viewDidLoad
    0.39
     Tissues
    0.39
    Einstellungen
    0.38
    awaiter
    0.38
    Activations Density 0.271%

    No Known Activations