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. 11-GEMMASCOPE-RES-16K
    6. 6273
    Prev
    Next
    INDEX
    Explanations

    elements and identifiers related to hierarchical or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.66
    HtmlAttribute
    -0.66
    Бахар
    -0.60
     باخ
    -0.58
     neige
    -0.58
    tagHelper
    -0.57
    EndContext
    -0.54
     colère
    -0.54
    awtextra
    -0.51
    GEBURTS
    -0.51
    POSITIVE LOGITS
    hdashline
    0.68
    __":
    0.61
     OFDb
    0.60
     /\.
    0.60
    ❋
    0.58
    :✨
    0.58
    therford
    0.58
    LabelTagHelper
    0.57
    }{*}{
    0.56
    로운
    0.55
    Activations Density 0.078%

    No Known Activations