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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 446
    Prev
    Next
    INDEX
    Explanations

    phrases related to clickable links and buttons

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

    "click"

    np_acts-logits-general · gemini-2.0-flash

    click followed by destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {}),
    -0.40
    RunWith
    -0.39
     Rutland
    -0.38
     Malden
    -0.37
     آز
    -0.36
    complexContent
    -0.36
     kelp
    -0.36
     conci
    -0.36
     As
    -0.36
    jersey
    -0.36
    POSITIVE LOGITS
     click
    0.99
     Click
    0.96
    click
    0.95
    Click
    0.94
     CLICK
    0.93
     clicks
    0.90
    CLICK
    0.89
    OnClickListener
    0.83
     clicked
    0.82
    Clicks
    0.82
    Activations Density 0.074%

    No Known Activations