© 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. 9009
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating differences or similarities in measurements or values

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

    comparative statements using "than" to express quantitative or qualitative differences between two entities.

    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
     surla
    -0.74
    UnusedPrivate
    -0.62
    apimachinery
    -0.57
    webElementGuid
    -0.57
    ftagPool
    -0.53
     tartalomajánló
    -0.53
    expandindo
    -0.51
    Климат
    -0.51
    resave
    -0.50
    zzleHttp
    -0.50
    POSITIVE LOGITS
     those
    2.59
    those
    2.16
    Those
    2.09
     Those
    2.02
     celui
    1.84
     ceux
    1.77
     quelli
    1.68
     celles
    1.66
     THOSE
    1.63
     celle
    1.60
    Activations Density 1.096%

    No Known Activations