© 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. 9580
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or comparisons

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

    the word "as" in listing or exemplifying contexts (such as examples).

    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
     demás
    -0.55
     übrigen
    -0.43
     beiden
    -0.42
     lainnya
    -0.40
     otros
    -0.39
     altri
    -0.38
     melakukannya
    -0.38
     båda
    -0.37
     restantes
    -0.37
     demais
    -0.37
    POSITIVE LOGITS
     those
    1.10
    those
    0.89
     الرياضيه
    0.85
     ceux
    0.84
     كومونز
    0.80
     celles
    0.79
     quelli
    0.78
    Those
    0.77
     autorytatywna
    0.76
     Those
    0.74
    Activations Density 0.528%

    No Known Activations