© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 276
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and intentions

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

    most likely, possibly

    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
     kasarigan
    -0.71
    windowFixed
    -0.58
    Personensuche
    -0.54
     transfieras
    -0.53
     autorytatywna
    -0.53
    Autoritní
    -0.53
    RenderAtEndOf
    -0.50
     समीक्षाओं
    -0.49
    outSlope
    -0.49
    BeginContext
    -0.49
    POSITIVE LOGITS
     probably
    0.82
    probably
    0.76
     Probably
    0.68
     probabilmente
    0.68
    Probably
    0.67
    おそらく
    0.66
     possibly
    0.64
     probablement
    0.63
     probablemente
    0.63
     likely
    0.63
    Activations Density 0.095%

    No Known Activations