© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2197
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to permissions and capabilities in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    preceding what is permitted

    np_acts-logits-general · gemini-2.0-flash

    enables or allows action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    Negative Logits
     invokingState
    -0.69
    AndEndTag
    -0.67
    stdc
    -0.64
    ThroughAttribute
    -0.64
    ScopeManager
    -0.61
     stiamo
    -0.57
    WarningLevel
    -0.54
     kanyang
    -0.54
     travaillons
    -0.53
     szolg
    -0.53
    POSITIVE LOGITS
     us
    1.28
     easy
    0.98
     them
    0.95
     him
    0.91
     flexibility
    0.88
     me
    0.88
     easier
    0.86
     greater
    0.85
     access
    0.84
     rapid
    0.78
    Activations Density 0.258%

    No Known Activations