© 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. 8112
    Prev
    Next
    INDEX
    Explanations

    questions that seek information or clarification

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

    Questions starting with "What"

    np_acts-logits-general · gemini-2.0-flash

    what kind of

    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
    <bos>
    -0.69
     suivantes
    -0.66
    StructEnd
    -0.65
    WriteTagHelper
    -0.59
    HandlerContext
    -0.58
     suivants
    -0.57
     mencionados
    -0.57
    DeleteBehavior
    -0.57
    abestanden
    -0.56
    ImageContext
    -0.55
    POSITIVE LOGITS
     kind
    1.26
     kinds
    1.13
     sort
    1.06
     type
    0.99
     types
    0.99
    kind
    0.97
     sorts
    0.94
     role
    0.87
     happens
    0.86
    sort
    0.85
    Activations Density 0.150%

    No Known Activations