© 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. 9-GEMMASCOPE-RES-131K
    11. 44172
    Prev
    Next
    INDEX
    Explanations

    instances of the word "completed" and its variations, indicating a focus on survey completion statuses

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

    act or state of completion

    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
    <bos>
    -0.77
    razine
    -0.56
     faibles
    -0.48
     direta
    -0.47
     Hodge
    -0.46
    arache
    -0.46
     uș
    -0.44
     tryck
    -0.44
     niebla
    -0.44
    MsgBox
    -0.44
    POSITIVE LOGITS
     completed
    1.91
    completed
    1.89
     Completed
    1.84
    Completed
    1.84
     COMPLETED
    1.55
    COMPLETED
    1.48
     completion
    1.42
     Completion
    1.39
    completion
    1.32
     completing
    1.28
    Activations Density 0.009%

    No Known Activations