© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 107555
    Prev
    Next
    INDEX
    Explanations

    references to technical terms and code elements related to software development and web services

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

    MUMLEY, MUM1, sourceforge

    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
    httphttps
    -0.79
    Хьажоргаш
    -0.68
     estekak
    -0.67
    Rujuakan
    -0.62
     EconPapers
    -0.61
     
    -0.59
     дописавши
    -0.58
    ̈́
    -0.58
    OCCURRED
    -0.58
     Roskov
    -0.58
    POSITIVE LOGITS
    MUM
    0.66
    migrationBuilder
    0.59
     SqlCommand
    0.54
     MUM
    0.47
    superuser
    0.46
    ResponseType
    0.45
    sourceforge
    0.44
    minlength
    0.44
     BorderRadius
    0.43
    primaryKey
    0.42
    Activations Density 0.001%

    No Known Activations