© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 71033
    Prev
    Next
    INDEX
    Explanations

    the word "exactly" in various contexts

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

    precise descriptions and confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    -------
    -0.51
     AssemblyCulture
    -0.47
    letoe
    -0.45
    FLD
    -0.45
    oredCriteria
    -0.44
    coer
    -0.44
     YB
    -0.43
    腆
    -0.43
    umbar
    -0.42
    vigil
    -0.42
    POSITIVE LOGITS
     what
    0.57
    ingly
    0.56
     opposite
    0.50
     why
    0.48
    Exactly
    0.45
     exactly
    0.45
    UnusedPrivate
    0.45
     how
    0.44
     Exactly
    0.43
    opposite
    0.43
    Activations Density 0.013%

    No Known Activations