© 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. 654
    Prev
    Next
    INDEX
    Explanations

    words related to categories and classifications, particularly in the context of sports and achievements

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

    structured data formatting with colons and category labels.

    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
    UnusedPrivate
    -0.53
    webElementXpaths
    -0.52
    LabelTagHelper
    -0.49
    üyada
    -0.45
     Meksiku
    -0.45
     <>",
    -0.43
    RegressionTest
    -0.42
    ➋
    -0.42
    المكان
    -0.41
    İstinadlar
    -0.41
    POSITIVE LOGITS
     Wikipedia
    0.88
     wiki
    0.82
     wikipedia
    0.76
     Wiki
    0.76
    wiki
    0.71
    Wikipedia
    0.68
     Wikipédia
    0.66
    Wiki
    0.64
    wikipedia
    0.64
     Wikimedia
    0.63
    Activations Density 0.403%

    No Known Activations