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. 13-GEMMASCOPE-RES-16K
    6. 11228
    Prev
    Next
    INDEX
    Explanations

    strings and identifiers used in coding or data structures

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

    syntax tokens that mark structure in code or markup, like tag delimiters, field prefixes, and operator-style punctuation.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.93
     snippetHide
    -0.85
    oredCriteria
    -0.69
    ReusableCell
    -0.65
     dAtA
    -0.65
     betweenstory
    -0.64
     '\\;'
    -0.64
     Seeder
    -0.64
     Numerade
    -0.63
    principalTable
    -0.62
    POSITIVE LOGITS
     Wiktionnaire
    0.55
    cbs
    0.53
    ​—
    0.52
    keda
    0.50
     pés
    0.49
    
    0.47
    metz
    0.47
    怪
    0.47
    iella
    0.47
    
    0.47
    Activations Density 0.081%

    No Known Activations