© 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. 4646
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in various contexts

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

    Comes after "S.", "U.S.", or "."

    np_acts-logits-general · gemini-2.0-flash

    . Ct

    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
     id
    -0.61
    [
    -0.59
    -
    -0.57
    iser
    -0.56
     art
    -0.56
     ed
    -0.54
     city
    -0.53
     night
    -0.53
     sub
    -0.52
     block
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.61
    ContentAsync
    0.59
     MessageBoxIcon
    0.58
    κτηρισ
    0.57
    prefixer
    0.57
     triom
    0.56
    󠁴
    0.55
    AutoresizingMask
    0.55
     chargés
    0.52
    endsection
    0.52
    Activations Density 0.027%

    No Known Activations