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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3647
    Prev
    Next
    INDEX
    Explanations

    HTML header tags, specifically focusing on their presence and structure

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

    HTML heading <h4> tags

    np_acts-logits-general · gemini-2.0-flash

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.74
    <h3>
    -0.72
    es
    -0.67
     mies
    -0.67
    ε
    -0.66
    lblNewLabel
    -0.64
    tutorials
    -0.61
    bootstrapcdn
    -0.61
    ᴇ
    -0.59
     Fails
    -0.57
    POSITIVE LOGITS
    theless
    1.15
    <th>
    1.01
     anúncio
    0.87
    ={`/
    0.87
     Monfieur
    0.81
     pleaſure
    0.79
    {{\
    0.78
     ſeveral
    0.78
    ductory
    0.78
     avoit
    0.78
    Activations Density 0.055%

    No Known Activations