© 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. 8318
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly in educational or creative 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
    userManager
    -0.40
    lar
    -0.37
     privilege
    -0.36
     Canopy
    -0.35
    -};
    -0.35
     resourceCulture
    -0.35
     publication
    -0.35
    age
    -0.35
     PRIV
    -0.35
     threat
    -0.35
    POSITIVE LOGITS
     says
    0.85
     remembers
    0.72
     mengaku
    0.71
     thinks
    0.69
     believes
    0.68
     berättar
    0.67
     spune
    0.67
     said
    0.67
     explains
    0.66
     mengatakan
    0.66
    Activations Density 0.266%

    No Known Activations