© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 12583
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to placing or adding items in a quantitative context

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

    after "put" or "putting"

    np_acts-logits-general · gemini-2.0-flash

    put in or put into

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    IVEREF
    -0.52
    +:+
    -0.49
    verifyException
    -0.49
    Географиясе
    -0.47
    tembre
    -0.44
    klis
    -0.43
    épendance
    -0.42
    gamon
    -0.42
     kaynağından
    -0.42
    contentLoaded
    -0.42
    POSITIVE LOGITS
     inserted
    0.79
     insert
    0.68
     put
    0.68
     placed
    0.66
     inserting
    0.63
     Placing
    0.63
     Put
    0.62
     Putting
    0.62
     insertion
    0.60
    Putting
    0.60
    Activations Density 0.599%

    No Known Activations