© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7074
    Prev
    Next
    INDEX
    Explanations

    references to positions, roles, and offices within political or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.40
    újo
    -0.37
    getBytes
    -0.35
    Handlung
    -0.33
    endphp
    -0.33
     Werke
    -0.33
     daran
    -0.33
     विश्वसनीयता
    -0.33
    úrate
    -0.32
    ɵɵ
    -0.32
    POSITIVE LOGITS
     reserved
    0.90
     vacated
    0.77
     coveted
    0.70
     occupied
    0.69
     Reserved
    0.69
     vacant
    0.68
     الرياضيه
    0.65
     reservation
    0.64
    reserved
    0.62
     RESERVED
    0.62
    Activations Density 0.508%

    No Known Activations