© 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. 30-GEMMASCOPE-RES-16K
    11. 15063
    Prev
    Next
    INDEX
    Explanations

    references to the Freedom of Information Act and related legal concepts

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

    Freedom of Information Act/requests

    np_acts-logits-general · gemini-2.0-flash

    Freedom of information requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.34
     stabili
    -0.33
    rzost
    -0.31
     concurso
    -0.31
     hemma
    -0.30
    業
    -0.30
     nies
    -0.29
     pleg
    -0.29
    cèse
    -0.29
    chufe
    -0.29
    POSITIVE LOGITS
     Freedom
    1.16
    Freedom
    1.03
     FO
    1.02
     freedom
    0.99
    freedom
    0.94
     FREEDOM
    0.88
     transparency
    0.82
     requests
    0.79
     transparencia
    0.78
     request
    0.77
    Activations Density 0.275%

    No Known Activations