© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    links to different resources or sections within a document

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

    HTML "a href" tags

    np_acts-logits-general · gemini-2.0-flash

    a href links

    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
     يتيمه
    -0.83
    WithIOException
    -0.76
     ويكيپيديا
    -0.65
     Мексичка
    -0.65
    MeasureSpec
    -0.63
    bcryptjs
    -0.62
     cherchés
    -0.59
    ValueStyle
    -0.58
     Castile
    -0.58
    Swiper
    -0.58
    POSITIVE LOGITS
     href
    1.25
    href
    0.77
    AnchorTagHelper
    0.69
    tagext
    0.67
     link
    0.61
     Link
    0.58
    Href
    0.58
    antMatchers
    0.57
    figcaption
    0.56
    link
    0.56
    Activations Density 0.044%

    No Known Activations