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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13381
    Prev
    Next
    INDEX
    Explanations

    prominent topic indicators or section headings in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.99
     "..\..\..\
    -0.96
     "..\..\
    -0.86
    تقاوى
    -0.85
     Chwiliwch
    -0.83
    Identyfik
    -0.81
    fromnode
    -0.80
    Tē
    -0.80
     кӀ
    -0.79
    bootstrapcdn
    -0.76
    POSITIVE LOGITS
    \{\\
    0.65
     StatelessWidget
    0.64
    ")));
    
    0.60
    ...");
    
    0.58
    évaluateur
    0.58
    ")))
    0.56
    "]];
    0.55
    tableFuture
    0.55
    ."));
    0.55
    ...}
    0.55
    Activations Density 0.095%

    No Known Activations