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. 15-GEMMASCOPE-RES-16K
    6. 5140
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols typically used in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.72
    EndGlobalSection
    -0.66
    utilisons
    -0.66
     disambiguazione
    -0.61
    prnewswire
    -0.61
    IBar
    -0.58
    ️⃣
    -0.58
    HasAnnotation
    -0.57
    tvguidetime
    -0.57
    CPtr
    -0.57
    POSITIVE LOGITS
    ()]);
    0.64
    ICEF
    0.58
    "]);
    
    0.58
     utafitiHapana
    0.58
    jeka
    0.56
    '));
    
    0.56
    TTE
    0.56
    DCE
    0.55
    )]=
    0.55
    NEU
    0.55
    Activations Density 0.532%

    No Known Activations