© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8897
    Prev
    Next
    INDEX
    Explanations

    curly braces and related formatting elements in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.66
    KommentareTeilen
    -0.65
    dotenv
    -0.62
     surla
    -0.59
    TargetException
    -0.56
    acebook
    -0.56
     snippetHide
    -0.54
     wireType
    -0.52
    ArgsConstructor
    -0.51
    useState
    -0.51
    POSITIVE LOGITS
    Tembelea
    0.63
     EconPapers
    0.51
    لسط
    0.48
    يميديا
    0.47
     дописавши
    0.47
    RegistryLite
    0.46
    bular
    0.46
    通販
    0.45
     gente
    0.45
     appliqué
    0.44
    Activations Density 0.242%

    No Known Activations