© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to maintaining safety and stability

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

    Follows "keep" or a variation of "keep"

    np_acts-logits-general · gemini-2.0-flash

    maintaining a state

    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
     Completed
    -0.59
     immédi
    -0.57
    SaveChangesAsync
    -0.57
    ALREADY
    -0.56
    MigrationBuilder
    -0.56
    ftagPool
    -0.56
     förm
    -0.56
    Already
    -0.55
    phazard
    -0.55
     udah
    -0.55
    POSITIVE LOGITS
     afloat
    0.92
     alive
    0.89
     sane
    0.72
     away
    0.69
     entertained
    0.69
     keep
    0.69
     kept
    0.68
     abreast
    0.68
    keep
    0.67
     cool
    0.67
    Activations Density 0.096%

    No Known Activations