© 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. 2459
    Prev
    Next
    INDEX
    Explanations

    references to positional or contextual descriptions within a framework or structure

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

    Nonsensical fragments and non-English language

    np_acts-logits-general · gemini-2.0-flash

    Russian technical or medical context

    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
    LookAnd
    -0.66
    Gambas
    -0.61
     kasarigan
    -0.59
     Ceux
    -0.56
     pinulongan
    -0.55
     disambiguazione
    -0.55
     contextLoads
    -0.54
     myſelf
    -0.52
     venner
    -0.52
    hinh
    -0.51
    POSITIVE LOGITS
    vode
    0.56
    imente
    0.51
    нении
    0.51
    czeniu
    0.47
    ванні
    0.46
    rode
    0.46
    шении
    0.45
    Pře
    0.45
    ствии
    0.45
    ={`${
    0.44
    Activations Density 0.051%

    No Known Activations