© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28303
    Prev
    Next
    INDEX
    Explanations

    occurrences of the beginning of sentences or paragraphs, particularly marking the start of new sections in the text

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

    mom, Eagles, feed, help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.69
    ()));
    -0.69
    }}],
    -0.68
    HasIndex
    -0.68
     {
    -0.67
    ²(
    -0.65
    Personendaten
    -0.63
    rungsseite
    -0.63
    ',
    -0.62
    ()));
    -0.61
    POSITIVE LOGITS
    tvguidetime
    0.72
     JpaRepository
    0.59
     ακόμα
    0.57
    annica
    0.57
    তথ্যসূত্র
    0.56
    otriva
    0.54
     betrekking
    0.54
    dasarkan
    0.54
    TargetException
    0.54
    िखित
    0.53
    Activations Density 0.326%

    No Known Activations