© 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. 8963
    Prev
    Next
    INDEX
    Explanations

    references to time periods, particularly durations and measurements of experience

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

    time periods measured in years.

    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
     lenker
    -0.33
    olkien
    -0.33
    Enclosure
    -0.32
     okreś
    -0.32
    équipements
    -0.31
     contactez
    -0.31
    пня
    -0.31
     kív
    -0.31
    >&
    -0.30
     Defined
    -0.30
    POSITIVE LOGITS
     worth
    0.66
    makeConstraints
    0.63
     '\\;'
    0.58
    ंदीखरीदारी
    0.56
    worth
    0.56
    RenderAtEndOf
    0.56
    XmlAccessType
    0.53
    IntoConstraints
    0.52
    ftagPool
    0.52
     arşivlendi
    0.51
    Activations Density 0.222%

    No Known Activations