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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1007
    Prev
    Next
    INDEX
    Explanations

    phrases concerning restrictions or prohibitions related to actions and affiliations

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

    Permission, prohibition, or allowance

    np_acts-logits-general · gemini-2.0-flash

    permission to speak or act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.77
    AnchorStyles
    -0.69
    </thead>
    -0.68
    IsContent
    -0.67
    interopRequire
    -0.62
     referenties
    -0.61
     виправивши
    -0.61
    χαν
    -0.61
    
    -0.60
    ValueStyle
    -0.59
    POSITIVE LOGITS
     darf
    0.79
     allowed
    0.69
     dürfen
    0.69
     phép
    0.68
     اجازه
    0.66
     durfte
    0.62
     permitted
    0.61
     boleh
    0.61
     permitido
    0.61
     mogen
    0.59
    Activations Density 0.511%

    No Known Activations