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. 5-GEMMASCOPE-RES-16K
    6. 2843
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to table structure and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.10
    mybatisplus
    -0.90
     protoimpl
    -0.83
    ThroughAttribute
    -0.82
     fieldNum
    -0.81
    oredCriteria
    -0.80
    enderror
    -0.80
    +#+#
    -0.78
     transfieras
    -0.77
     otomatig
    -0.75
    POSITIVE LOGITS
    ":[{
    0.68
    álva
    0.60
    ISupport
    0.59
    )(((
    0.57
    csname
    0.56
    figcaption
    0.55
    netbeans
    0.55
     Jeune
    0.54
    <caption>
    0.52
     نسخة
    0.52
    Activations Density 0.146%

    No Known Activations