© 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. 18-GEMMASCOPE-RES-16K
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    references to NPR and its content, including titles, segments, and reporting details

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

    news sources or radio stations

    np_acts-logits-general · gemini-2.0-flash

    NPR, public radio, news broadcasters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thủy
    -0.45
    jet
    -0.44
     svin
    -0.43
     ener
    -0.41
    coles
    -0.41
     pages
    -0.41
     Model
    -0.41
     Agarwal
    -0.40
     Pages
    -0.40
    itigation
    -0.40
    POSITIVE LOGITS
     NPR
    1.19
    NPR
    1.07
    UserScript
    0.87
    npr
    0.77
     pinulongan
    0.74
    VOA
    0.72
    ScopeManager
    0.72
    parsedMessage
    0.72
     NHK
    0.71
    SOUNDBITE
    0.71
    Activations Density 0.118%

    No Known Activations