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. 3129
    Prev
    Next
    INDEX
    Explanations

    headings or titles within the document

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

    HTML heading tags (h1, h2, h3, etc.)

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and section headers

    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
     الرياضيه
    -0.88
    Géographie
    -0.72
    ípio
    -0.71
    లాలు
    -0.70
    enderror
    -0.68
    Poloha
    -0.68
    Démographie
    -0.68
    ManyToMany
    -0.65
    latLng
    -0.65
    Друзья
    -0.63
    POSITIVE LOGITS
    <h2>
    1.86
    <th>
    1.05
    <h3>
    1.00
    <h1>
    0.99
    </h2>
    0.91
     <<<<<<<<<<<<<<
    0.89
     contextLoads
    0.87
    <h6>
    0.86
     juſt
    0.85
    <h4>
    0.83
    Activations Density 0.001%

    No Known Activations