© 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. 624
    Prev
    Next
    INDEX
    Explanations

    phrases related to gradual changes and increasing intensity

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

    words or phrases indicating progression, intensification, or comparative increase.

    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
     للاسماء
    -0.51
     ***!
    -0.47
    setVerticalGroup
    -0.47
     palju
    -0.45
    mucho
    -0.43
     alertDialog
    -0.40
     immediate
    -0.40
    ⓘ
    -0.39
    enderror
    -0.39
    ียบ
    -0.39
    POSITIVE LOGITS
     increasingly
    1.48
     progressively
    1.43
    越来越
    1.31
    越來越
    1.30
     increasing
    1.25
    increasing
    1.20
    Increasing
    1.18
     semakin
    1.17
     Increasing
    1.17
     coraz
    1.15
    Activations Density 0.651%

    No Known Activations