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. 9-GEMMASCOPE-RES-131K
    6. 45925
    Prev
    Next
    INDEX
    Explanations

    references to the properties and interactions of oil and water in emulsions

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

    organic and aqueous phases

    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
    MigrationBuilder
    -0.52
    })->
    -0.40
    Twig
    -0.39
    DispatchToProps
    -0.38
    TableBody
    -0.38
    smarty
    -0.38
     ujednoznacz
    -0.38
    gameserver
    -0.38
     laude
    -0.38
    存于互联网档案馆
    -0.35
    POSITIVE LOGITS
    Ufficio
    0.44
    ➟
    0.41
    esez
    0.41
     незавершена
    0.41
    afficheront
    0.40
     initComponents
    0.40
    帖最后由
    0.39
     resourceCulture
    0.38
     separator
    0.37
     الحره
    0.37
    Activations Density 0.182%

    No Known Activations