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

    Neuronpedia

    APICircuit 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. 15724
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers and associated data structures

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

    Numbers followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    timestamps and subtitles

    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
    aben
    -0.64
    asibility
    -0.57
     bè
    -0.54
    salm
    -0.54
     createState
    -0.51
    cloudfront
    -0.51
    ABILIDAD
    -0.50
     otomatig
    -0.50
    thon
    -0.49
    名叫
    -0.49
    POSITIVE LOGITS
    />";
    0.71
     متعلقه
    0.70
    Personensuche
    0.69
     betweenstory
    0.67
     Autorizaciones
    0.67
    ⓘ
    0.65
     iArr
    0.63
    ItemBackground
    0.63
    зец
    0.61
    astify
    0.60
    Activations Density 0.552%

    No Known Activations