© 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. 15758
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing possibility or potential actions

    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
     CreateTagHelper
    -0.82
    ientras
    -0.62
     autorytatywna
    -0.61
     avoient
    -0.61
    étoit
    -0.57
     ***!
    -0.57
    uaikan
    -0.56
    errHandler
    -0.55
     wireType
    -0.54
    AndEndTag
    -0.54
    POSITIVE LOGITS
     potential
    0.55
     Potential
    0.46
     Prospective
    0.40
     probable
    0.40
    potential
    0.39
     futurs
    0.39
     prospective
    0.39
    可
    0.38
    ematic
    0.38
     yyl
    0.38
    Activations Density 0.441%

    No Known Activations