© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    terms related to the actions or conditions of 'evasion' or 'evacuating'

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

    starting with "Ev" or "ev"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ev

    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
     '\\;'
    -0.70
    حياته
    -0.68
    حياتها
    -0.63
    ConstraintMaker
    -0.60
    esModule
    -0.59
    DeleteBehavior
    -0.57
     kaynağından
    -0.54
    toBeTruthy
    -0.54
     صوتيه
    -0.54
    MethodManager
    -0.54
    POSITIVE LOGITS
     ev
    0.71
     jsPsych
    0.66
     Ev
    0.60
    asive
    0.60
    ev
    0.58
    Ev
    0.56
    AutoScaleMode
    0.55
     evoc
    0.54
     Eva
    0.51
     Evapor
    0.50
    Activations Density 0.149%

    No Known Activations