© 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. 70401
    Prev
    Next
    INDEX
    Explanations

    occurrences of variations of the word "squash" and its derivatives, indicating a focus on those terms

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

    squ prefix

    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
     României
    -0.43
     snippetHide
    -0.40
     <<<<<<<<<<<<<<
    -0.36
     كومونز
    -0.36
    parsedMessage
    -0.34
    Népesség
    -0.34
    WriteTagHelper
    -0.34
    PMailer
    -0.33
     adul
    -0.33
     polos
    -0.33
    POSITIVE LOGITS
     Squ
    1.29
     squ
    1.27
    Squ
    1.16
    squ
    1.12
     SQU
    1.00
    SQU
    0.80
     squa
    0.80
     squeak
    0.79
     sq
    0.76
     Sq
    0.74
    Activations Density 0.019%

    No Known Activations