Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 5033
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and data types

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

    Code snippets and programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    local object int 8

    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
    ViewFeatures
    -0.49
    ništ
    -0.45
    AndPassword
    -0.44
    setGeometry
    -0.41
    ity
    -0.41
    롯
    -0.40
     comunic
    -0.40
    存在的
    -0.40
    вяз
    -0.39
    WithFormat
    -0.39
    POSITIVE LOGITS
    windowFixed
    0.71
     EconPapers
    0.69
     disambiguazione
    0.65
    ieteur
    0.65
    djangoproject
    0.64
     ◄
    0.64
    帖最后由
    0.62
     Riproduzione
    0.61
     חיצוניים
    0.61
    rrggbb
    0.60
    Activations Density 0.019%

    No Known Activations