© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14307
    Prev
    Next
    INDEX
    Explanations

    specific medical and research terms related to clinical studies

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

    Basque country region/language

    np_acts-logits-general · gemini-2.0-flash

    Arri, rena, eber, Bilbao

    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
    WV
    -0.42
    opy
    -0.41
    Ci
    -0.41
     Inferno
    -0.41
     étendue
    -0.40
     Lovell
    -0.39
    नों
    -0.39
     ще
    -0.38
    PRM
    -0.38
    uly
    -0.37
    POSITIVE LOGITS
     MainAxisSize
    0.73
    ValueStyle
    0.69
    DeleteBehavior
    0.66
    WriteTagHelper
    0.65
    uxxxx
    0.65
    ">//
    0.63
     TextAppearance
    0.62
     estekak
    0.62
    XmlType
    0.62
    ⓧ
    0.61
    Activations Density 0.083%

    No Known Activations