© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9649
    Prev
    Next
    INDEX
    Explanations

    sections related to bibliographic or citation information

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

    bibliographic citations and reference formatting in academic or technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ITUTE
    -0.37
    ésultat
    -0.36
    MigrationBuilder
    -0.36
     playera
    -0.35
    段
    -0.32
     alá
    -0.32
     acquaintance
    -0.32
     máxima
    -0.31
     evolucion
    -0.31
     continuidad
    -0.31
    POSITIVE LOGITS
     ISBN
    1.38
    ISBN
    1.27
     isbn
    1.12
    isbn
    0.96
     ISSN
    0.93
    ISSN
    0.81
     EAN
    0.71
     UPC
    0.70
     barcode
    0.69
     Barcode
    0.67
    Activations Density 0.277%

    No Known Activations