© 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
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15497
    Prev
    Next
    INDEX
    Explanations

    instances of calls to action related to clicking or selecting options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malden
    -0.37
     recovering
    -0.36
     conservation
    -0.36
     genome
    -0.35
    }\|
    -0.34
    ]")]
    -0.34
     nal
    -0.34
     burden
    -0.34
     NgModule
    -0.34
     Re
    -0.33
    POSITIVE LOGITS
     click
    3.02
    click
    2.83
     Click
    2.81
    Click
    2.72
     clicks
    2.55
     clicked
    2.47
     CLICK
    2.44
    CLICK
    2.36
     clicking
    2.33
    clicking
    2.19
    Activations Density 0.106%

    No Known Activations