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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 892
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure elements, particularly focusing on environments and formatting commands

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

    structured elements related to document formatting

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

    html and latex markup

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ⓧ
    -0.73
    GenerationType
    -0.54
    AndEndTag
    -0.51
    AddTagHelper
    -0.50
    stylers
    -0.50
    +#+#
    -0.49
    inSlope
    -0.49
    Geplaatst
    -0.48
    jsonPath
    -0.47
    AuthGuard
    -0.46
    POSITIVE LOGITS
    hassee
    0.71
    velt
    0.67
    IntoConstraints
    0.64
     initComponents
    0.60
    __':
    0.58
    BoxShadow
    0.57
    Παραπομπές
    0.56
    ervor
    0.56
    __':
    
    0.56
    crollView
    0.55
    Activations Density 0.051%

    No Known Activations