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. 10-GEMMASCOPE-RES-16K
    6. 3042
    Prev
    Next
    INDEX
    Explanations

    structured elements in documents or code, particularly related to item attributes and metadata

    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
     <>",
    -0.66
    AutoScaleMode
    -0.64
     fut
    -0.63
    hahn
    -0.60
    BuildContext
    -0.59
    kloped
    -0.58
    AsUp
    -0.58
    ukunfts
    -0.57
    autorest
    -0.57
    تقاوى
    -0.56
    POSITIVE LOGITS
    <eos>
    0.68
     Audiodateien
    0.67
    endphp
    0.62
     الحره
    0.60
    ↵↵
    0.60
    isRequired
    0.54
    endforeach
    0.51
    reportWebVitals
    0.51
    )))));
    0.50
    addGap
    0.50
    Activations Density 0.583%

    No Known Activations