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. 20-GEMMASCOPE-RES-16K
    6. 12644
    Prev
    Next
    INDEX
    Explanations

    information related to gene inclusion and classification in biological research

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

    Exclusion or addition related to files, data, or items

    np_acts-logits-general · gemini-2.0-flash

    listing things and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.70
    LabelTagHelper
    -0.63
    Datuak
    -0.60
     HasFactory
    -0.58
    SourceChecksum
    -0.55
     rând
    -0.55
    Демографія
    -0.54
     occident
    -0.52
     liné
    -0.52
    ClientSize
    -0.51
    POSITIVE LOGITS
     special
    1.05
     specialty
    0.93
    special
    0.86
     hybrids
    0.85
     hybrid
    0.84
     Special
    0.84
     speciality
    0.82
    specialty
    0.79
     specials
    0.79
    Specialty
    0.77
    Activations Density 1.373%

    No Known Activations