© 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. 20-GEMMASCOPE-RES-16K
    11. 8071
    Prev
    Next
    INDEX
    Explanations

    the term "Dol" and its variations, indicating a focus on a specific name or concept

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

    Tokens starting with "Dol" or "ox"

    np_acts-logits-general · gemini-2.0-flash

    Dolberry, Dolmen, Doxycycline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.59
    GOTREF
    -0.53
    chyma
    -0.51
    emf
    -0.51
     Celui
    -0.47
     ListTile
    -0.47
    trane
    -0.47
    ulina
    -0.45
    FirstResponder
    -0.45
    </tfoot>
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.76
    цездатний
    0.70
    SDAY
    0.66
     TestBed
    0.64
    indd
    0.63
    contentLoaded
    0.63
    abetes
    0.63
    uments
    0.61
    cosa
    0.61
    vician
    0.60
    Activations Density 0.142%

    No Known Activations