© 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. 24-GEMMASCOPE-RES-16K
    11. 9065
    Prev
    Next
    INDEX
    Explanations

    references to targets and target-related terms in a scientific context

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

    "target" and its derivatives

    np_acts-logits-general · gemini-2.0-flash

    target regions and enrichment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunAsync
    -0.47
     stø
    -0.47
    Anhalt
    -0.46
    MigrationBuilder
    -0.46
     ouverts
    -0.46
     colorés
    -0.46
     hemma
    -0.45
     partant
    -0.44
    <![
    -0.44
    setVerticalGroup
    -0.44
    POSITIVE LOGITS
    ted
    1.07
    ="_
    1.05
    ting
    1.01
     audience
    0.93
     Audience
    0.82
    SdkVersion
    0.78
    ='_
    0.76
     audiences
    0.72
    FormTagHelper
    0.70
    Audience
    0.69
    Activations Density 0.086%

    No Known Activations