Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 739
    Prev
    Next
    INDEX
    Explanations

    descriptions of heating devices and systems

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

    powered, heated or motorized devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Schall
    -0.33
     œil
    -0.33
     committed
    -0.32
    ścic
    -0.31
    ści
    -0.31
     chụp
    -0.30
     visiting
    -0.29
     Versch
    -0.29
     veľ
    -0.29
     feil
    -0.29
    POSITIVE LOGITS
     ब्रेकडाउन
    0.62
    IBOutlet
    0.62
    IntoConstraints
    0.58
     electrically
    0.57
    Życiorys
    0.56
     actuators
    0.55
    enoid
    0.54
     eléctrica
    0.54
    expandindo
    0.53
    cosse
    0.52
    Activations Density 0.042%

    No Known Activations