© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11516
    Prev
    Next
    INDEX
    Explanations

    terms related to community engagement and gender dynamics in the context of family planning discussions

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

    "[Adjective] level" or "level" as a noun

    np_acts-logits-general · gemini-2.0-flash

    scopes followed by level

    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
    RegressionTest
    -0.65
    PerformLayout
    -0.57
    MessageTagHelper
    -0.52
    enumi
    -0.50
    帖最后由
    -0.47
     joaat
    -0.47
    WritableDatabase
    -0.46
    ضم
    -0.46
    contentLoaded
    -0.44
    häuse
    -0.44
    POSITIVE LOGITS
     level
    4.46
    level
    3.96
     Level
    3.73
    Level
    3.69
     LEVEL
    3.60
     levels
    3.49
    LEVEL
    3.35
    levels
    3.09
     Levels
    3.05
     nivel
    3.01
    Activations Density 0.559%

    No Known Activations