© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9604
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associated titles or credentials

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

    author names and initials in academic citations and bibliographies.

    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
     AssemblyCulture
    -0.65
    #+#
    -0.60
    liceerd
    -0.59
    Хьажоргаш
    -0.58
     MainAxisSize
    -0.58
    ViewFeatures
    -0.57
    MessageWindow
    -0.57
    KommentareTeilen
    -0.57
    XmlAccessorType
    -0.57
    SharedDtor
    -0.56
    POSITIVE LOGITS
     J
    0.73
     E
    0.65
     M
    0.62
     L
    0.62
     H
    0.60
     C
    0.59
     R
    0.55
     A
    0.54
     P
    0.54
     W
    0.54
    Activations Density 0.343%

    No Known Activations