© 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. 9005
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to healthcare interventions and studies

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

    grammatical transformations like plurals, verb conjugations, and word variations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    the beginning of sequences (start-of-sequence tokens).

    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
    parsedMessage
    -1.20
    <unused28>
    -0.98
    <unused14>
    -0.98
    [@BOS@]
    -0.98
    <unused51>
    -0.98
    <unused79>
    -0.98
    <unused41>
    -0.98
    <unused52>
    -0.98
    <unused17>
    -0.98
    <unused8>
    -0.98
    POSITIVE LOGITS
    <unused61>
    0.25
    <unused62>
    0.23
     vœ
    0.23
    Witam
    0.21
    <unused63>
    0.21
     nôtre
    0.20
     hendes
    0.20
     usw
    0.20
     vôtre
    0.20
     culte
    0.18
    Activations Density 96.830%

    No Known Activations