© 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. 17-GEMMASCOPE-RES-16K
    11. 9233
    Prev
    Next
    INDEX
    Explanations

    tokens or markers that signify the beginning of a new section or concept in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.98
     كومونز
    -0.91
    SharedCtor
    -0.90
     tartalomajánló
    -0.88
    rrggbb
    -0.88
    aarrggbb
    -0.85
    XmlEnum
    -0.82
    SharedDtor
    -0.80
    SourceChecksum
    -0.77
    AddTagHelper
    -0.77
    POSITIVE LOGITS
    Font
    0.57
     ngu
    0.48
    lique
    0.47
     font
    0.47
     noten
    0.47
    Mate
    0.46
     Font
    0.45
     fonts
    0.44
    Teraz
    0.43
    Pur
    0.43
    Activations Density 0.010%

    No Known Activations