© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7804
    Prev
    Next
    INDEX
    Explanations

    information related to environmental conservation and restoration efforts

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

    Quantities or counts of people

    np_acts-logits-general · gemini-2.0-flash

    quantities of members or participants

    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
     يتيمه
    -0.94
    Ծանոթ
    -0.73
     ujednoznacz
    -0.72
    Viitteet
    -0.70
    ArgsConstructor
    -0.68
    MigrationBuilder
    -0.67
     ويكيپيديا
    -0.66
    ValueStyle
    -0.66
    SequentialGroup
    -0.65
    droje
    -0.63
    POSITIVE LOGITS
     ranging
    1.23
     spanning
    1.17
     covering
    1.04
     spread
    1.01
     across
    0.91
    spanning
    0.86
     encompassing
    0.85
     spans
    0.83
    ranging
    0.83
     répar
    0.82
    Activations Density 0.382%

    No Known Activations