© 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. 4456
    Prev
    Next
    INDEX
    Explanations

    references to role models, especially female figures in advocacy and influence

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

    "model" or "inspiration"

    np_acts-logits-general · gemini-2.0-flash

    role model, inspiration, example

    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
    seamnă
    -0.59
    ViewFeatures
    -0.58
    IsPostBack
    -0.54
    __":
    -0.54
    __':
    -0.52
     ExecuteAsync
    -0.52
    ScopeManager
    -0.52
     Diretto
    -0.51
    IBAction
    -0.51
    webpack
    -0.51
    POSITIVE LOGITS
     Vorbild
    1.70
     model
    1.58
     role
    1.57
     inspiration
    1.57
     example
    1.52
     models
    1.51
     voorbeeld
    1.47
     modèles
    1.42
     modèle
    1.36
     Role
    1.35
    Activations Density 0.234%

    No Known Activations