Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4326
    Prev
    Next
    INDEX
    Explanations

    queries related to programming or database management tasks, specifically focusing on error handling or variable manipulation

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

    Followed by a verb in Spanish

    np_acts-logits-general · gemini-2.0-flash

    Spanish and Portuguese technical text

    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
    CDATA
    -0.52
    nta
    -0.48
    ser
    -0.47
     waiting
    -0.46
     necessarily
    -0.45
     treo
    -0.45
    être
    -0.44
     awaiting
    -0.44
     bao
    -0.44
     razie
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
    RegistryLite
    0.82
    writeFieldEnd
    0.71
    expandindo
    0.70
     EconPapers
    0.70
    matchCondition
    0.69
     كومونز
    0.68
     мәкал
    0.65
    зулта
    0.65
     дописавши
    0.64
    Activations Density 0.036%

    No Known Activations