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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6703
    Prev
    Next
    INDEX
    Explanations

    conditional statements and their branches in programming code

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

    sets of conditional statements and branching logic in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ConstraintMaker
    -0.73
     fopen
    -0.62
    SaveChanges
    -0.62
    حياته
    -0.61
    Історія
    -0.61
     "@/
    -0.59
    eeqa
    -0.58
    حياتها
    -0.57
    %%
    
    -0.55
    nestjs
    -0.55
    POSITIVE LOGITS
    VIAF
    0.85
     дописавши
    0.70
     الحره
    0.70
     PyLong
    0.64
    chkin
    0.63
    ContentAlignment
    0.63
    tonode
    0.62
    hline
    0.60
    ✭
    0.59
    MethodManager
    0.59
    Activations Density 0.044%

    No Known Activations