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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 14885
    Prev
    Next
    INDEX
    Explanations

    links and references in the text

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

    "Link" or "links" followed by preposition "to"

    np_acts-logits-general · gemini-2.0-flash

    link, links, linked, linkage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.74
     SRT
    -0.67
     Borel
    -0.66
     saira
    -0.65
    newState
    -0.65
     chalkboard
    -0.65
     Offen
    -0.64
     UnityEditor
    -0.64
     BoxDecoration
    -0.63
    Subviews
    -0.63
    POSITIVE LOGITS
     link
    1.63
     LINK
    1.60
     Link
    1.59
     links
    1.55
    link
    1.46
    links
    1.44
    LINK
    1.43
     Links
    1.41
    Link
    1.40
     LINKS
    1.36
    Activations Density 0.073%

    No Known Activations