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. 85594
    Prev
    Next
    INDEX
    Explanations

    references to sources and citations of support or contributions

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

    incoming from a source

    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
    jsxFileName
    -0.67
     autorytatywna
    -0.54
    rungsseite
    -0.52
    férés
    -0.52
     ciò
    -0.51
    exels
    -0.48
    closedir
    -0.47
     مشين
    -0.47
     affitto
    -0.47
    neſs
    -0.47
    POSITIVE LOGITS
     by
    0.35
     تضيفلها
    0.34
     sonre
    0.33
    摇摇头
    0.33
    来自
    0.33
     }^{[
    0.33
     local
    0.32
    ?}",
    0.32
    pfen
    0.32
     verdaderos
    0.32
    Activations Density 0.040%

    No Known Activations