© 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. 16-GEMMASCOPE-RES-16K
    11. 6884
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific journals and articles related to academic literature

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

    Abbreviations and initials

    np_acts-logits-general · gemini-2.0-flash

    ajedrez and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rousse
    -0.64
    u
    -0.53
    CARE
    -0.51
     ater
    -0.51
     Exteriores
    -0.50
    coming
    -0.50
    renos
    -0.48
    aas
    -0.48
    nam
    -0.48
     Woodlands
    -0.48
    POSITIVE LOGITS
    ournal
    0.77
    principalColumn
    0.70
    Kaj
    0.70
     Kaj
    0.70
    PathVariable
    0.69
     tj
    0.69
    AddTagHelper
    0.69
    PathParam
    0.67
     Mij
    0.67
    czaj
    0.67
    Activations Density 0.283%

    No Known Activations