© 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 EvalsExportsinterp-engineNEWAPI 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. 383
    Prev
    Next
    INDEX
    Explanations

    phrases related to political behaviors and actions

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

    preceding verbs, especially forms of "to be"

    np_acts-logits-general · gemini-2.0-flash

    studies are missing

    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
    elemField
    -0.75
     للمعارف
    -0.57
    toHaveBeenCalled
    -0.57
    fortawesome
    -0.54
    SourceChecksum
    -0.54
    HasIndex
    -0.53
    knex
    -0.50
    IsMutable
    -0.50
    Knows
    -0.49
     strtok
    -0.49
    POSITIVE LOGITS
     are
    3.20
     were
    2.44
     aren
    2.08
     have
    1.95
    are
    1.83
     weren
    1.79
     ARE
    1.72
     são
    1.64
     sont
    1.62
    were
    1.61
    Activations Density 3.871%

    No Known Activations