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. 4116
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure manipulation and programming commands

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

    Mathematical or code-related symbols and expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and code structure

    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
    om
    -0.43
    ی
    -0.43
    mi
    -0.41
    com
    -0.41
     nuggets
    -0.40
    棘
    -0.39
    her
    -0.39
    id
    -0.39
    ज
    -0.39
    >
    -0.38
    POSITIVE LOGITS
    UserScript
    1.04
     ddelweddau
    1.02
    //
    0.95
    IntoConstraints
    0.94
    TagMode
    0.91
    ThroughAttribute
    0.90
    DIPSETTING
    0.84
     Wiktionnaire
    0.83
    <?
    0.83
    Personensuche
    0.82
    Activations Density 1.719%

    No Known Activations