© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3153
    Prev
    Next
    INDEX
    Explanations

    instances of "set" and its variations to indicate initiation or establishment of plans and goals

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the phrase "set" followed by "a" and related words like "high," "bar," "tone," "another," "record," "the," or "simple" that establish standards, goals, or expectations.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     يتيمه
    -0.48
    tagHelperRunner
    -0.42
     Италијани
    -0.41
    hideLoading
    -0.38
    MergeFrom
    -0.38
    WebElementEntity
    -0.37
     vacacionales
    -0.37
    nasel
    -0.36
    writeFieldEnd
    -0.36
    Pranala
    -0.35
    POSITIVE LOGITS
     Setting
    0.83
     aside
    0.81
     setting
    0.75
     set
    0.75
    Setting
    0.71
    setting
    0.67
    aside
    0.65
     SETTING
    0.63
     forth
    0.60
     precedent
    0.60
    Activations Density 0.089%

    No Known Activations