© 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. 27787
    Prev
    Next
    INDEX
    Explanations

    different forms of the beginning of sentences or phrases, specifically the markers of new thoughts or paragraphs

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

    trust or faith

    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
    RectangleBorder
    -0.59
    koa
    -0.58
    เทศ
    -0.53
    tagHelperRunner
    -0.53
    tagHelper
    -0.52
     unsuccessfully
    -0.52
    ặng
    -0.51
    ieden
    -0.51
     ITIS
    -0.50
    aarrggbb
    -0.49
    POSITIVE LOGITS
     trust
    1.47
     trusting
    1.28
    Trust
    1.25
    trust
    1.23
     trusted
    1.20
     Trust
    1.20
     vertrouwen
    1.18
     TRUST
    1.18
     confiance
    1.17
     Vertrauen
    1.17
    Activations Density 0.090%

    No Known Activations