© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2337
    Prev
    Next
    INDEX
    Explanations

    instances of commands or prompts related to clicking or interacting with content

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

    "click" and related actions

    np_acts-logits-general · gemini-2.0-flash

    Click for more

    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
     gend
    -0.47
     conservation
    -0.43
     NgModule
    -0.43
    otho
    -0.43
     Zend
    -0.42
     Malden
    -0.41
     незавершена
    -0.40
     genome
    -0.40
    mergeFrom
    -0.40
    ]")]
    -0.39
    POSITIVE LOGITS
     click
    2.38
    click
    2.30
     Click
    2.20
    Click
    2.20
     clicks
    1.96
     CLICK
    1.92
     clicked
    1.85
    CLICK
    1.85
     clicking
    1.76
    clicking
    1.70
    Activations Density 0.094%

    No Known Activations