© 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. 22-GEMMASCOPE-RES-16K
    11. 4590
    Prev
    Next
    INDEX
    Explanations

    terms related to risks and accidents

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

    preceding time units

    np_acts-logits-general · gemini-2.0-flash

    annual and daily frequency

    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
    RectangleBorder
    -0.67
    StackNavigator
    -0.66
    Xna
    -0.59
     SwitchCompat
    -0.58
     createState
    -0.57
    новништво
    -0.56
     MainAxisSize
    -0.55
     /\.(
    -0.54
     nameof
    -0.53
     <=",
    -0.53
    POSITIVE LOGITS
     every
    3.15
     each
    2.74
    every
    2.66
     setiap
    2.46
     chaque
    2.46
    Every
    2.32
     annually
    2.29
     ogni
    2.27
     varje
    2.26
     Every
    2.25
    Activations Density 0.702%

    No Known Activations