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. 2137
    Prev
    Next
    INDEX
    Explanations

    elements of concern or caution in various contexts

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

    Follows certain words (off, okay, photos, economy, wrong)

    np_acts-logits-general · gemini-2.0-flash

    dashes or hyphens

    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
    \{\\
    -0.82
    rungsseite
    -0.80
     Мексичка
    -0.76
    DrawerToggle
    -0.69
     وتسجيلات
    -0.67
     Перейти
    -0.66
    TagMode
    -0.65
     مشين
    -0.64
    ثيق
    -0.64
    RegistryLite
    -0.63
    POSITIVE LOGITS
     -
    1.89
     –
    1.84
     —
    1.53
     --
    1.53
    —
    1.52
    --
    1.47
     — 
    1.25
    €“
    1.25
    –
    1.24
    ---
    1.21
    Activations Density 0.729%

    No Known Activations