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. 20-GEMMASCOPE-RES-16K
    6. 10678
    Prev
    Next
    INDEX
    Explanations

    phrases related to careful planning or organization in various contexts

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

    Personal items or possessions

    np_acts-logits-general · gemini-2.0-flash

    Possessions and property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseWriter
    -0.75
    kháu
    -0.63
    zkopf
    -0.58
    __*/
    -0.57
    LEncoder
    -0.53
    LookAnd
    -0.52
     ویکی‌پدیا
    -0.52
    createCanvas
    -0.49
    sistency
    -0.49
    DoubleQuotes
    -0.48
    POSITIVE LOGITS
     items
    1.46
     Items
    1.26
     ITEMS
    1.16
     item
    1.09
     possessions
    1.08
    items
    1.07
     itens
    1.05
    Items
    1.05
     belongings
    1.03
     treasures
    1.02
    Activations Density 0.274%

    No Known Activations