© 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. 18-GEMMASCOPE-RES-16K
    11. 4016
    Prev
    Next
    INDEX
    Explanations

    multiple instances of specific numerical codes or structured data representations

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

    Appears before a number followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    packed_sfixed64

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    By
    -0.52
    ceptable
    -0.49
     Offisielt
    -0.47
    DoubleQuotes
    -0.46
    king
    -0.45
     dėl
    -0.45
     ajan
    -0.44
     esterna
    -0.43
    by
    -0.43
     By
    -0.43
    POSITIVE LOGITS
    JspWriter
    0.96
    RenderAtEndOf
    0.81
    MLLoader
    0.76
    TagMode
    0.74
     nakalista
    0.72
    TintMode
    0.70
     Мексичка
    0.68
     متعلقه
    0.68
     ***!
    0.68
    oredCriteria
    0.67
    Activations Density 0.429%

    No Known Activations