© 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 EvalsExportsAPI 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. 10358
    Prev
    Next
    INDEX
    Explanations

    technical terms related to information transfer and networking

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

    Values from environment variables

    np_acts-logits-general · gemini-2.0-flash

    environment variables

    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
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.54
    XtraGrid
    -0.54
    numerusform
    -0.51
    FetchType
    -0.51
    featureID
    -0.49
    mær
    -0.49
    DeleteBehavior
    -0.48
     GenerationType
    -0.47
    addGap
    -0.47
    CascadeType
    -0.47
    POSITIVE LOGITS
     env
    1.06
     environment
    1.04
     Environment
    1.04
    env
    0.99
    Env
    0.97
    Environment
    0.96
    environment
    0.94
     ENVIRONMENT
    0.94
     ENV
    0.93
    ENV
    0.93
    Activations Density 0.283%

    No Known Activations