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. 9104
    Prev
    Next
    INDEX
    Explanations

    instances of common conjunctions and prepositions in text

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

    "future", "present", "previous", or "current"

    np_acts-logits-general · gemini-2.0-flash

    in future, present, previous, current, recent

    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
    abestanden
    -0.97
     autorytatywna
    -0.95
    IUrlHelper
    -0.80
     ModelExpression
    -0.75
    RegistryLite
    -0.73
     wireType
    -0.72
    SourceChecksum
    -0.71
    protoimpl
    -0.70
     ویکی‌پدی
    -0.70
    TagMode
    -0.70
    POSITIVE LOGITS
    IsPostBack
    0.55
    eake
    0.51
     vectoriales
    0.50
    ernan
    0.49
     diras
    0.49
     secos
    0.49
     acoso
    0.48
     colesterol
    0.47
    grunns
    0.47
     médec
    0.46
    Activations Density 0.512%

    No Known Activations