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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 99339
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "have."

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

    has/have followed by past participles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кислота
    -0.39
    当時の
    -0.37
     zav
    -0.35
    //////////////
    -0.35
     droog
    -0.34
     toys
    -0.34
     style
    -0.32
    rawQuery
    -0.31
     ways
    -0.31
     formulario
    -0.31
    POSITIVE LOGITS
    depuis
    0.67
     tentatively
    0.63
    featureID
    0.62
     vært
    0.60
     been
    0.59
    been
    0.59
     يتيمه
    0.59
     zostać
    0.57
     derzeit
    0.57
     repeatedly
    0.57
    Activations Density 0.066%

    No Known Activations