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. 2978
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements

    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
    <eos>
    -0.74
    ↵↵
    -0.51
     St
    -0.43
     Service
    -0.40
    Service
    -0.39
    St
    -0.39
     general
    -0.39
     թվական
    -0.38
    fillType
    -0.37
     yana
    -0.37
    POSITIVE LOGITS
     newOwner
    0.78
    帖最后由
    0.77
    </caption>
    0.75
    InjectAttribute
    0.75
    MemoryWarning
    0.73
     handleMessage
    0.73
    </em>
    0.72
    はじめに
    0.72
     initComponents
    0.71
     дописавши
    0.71
    Activations Density 0.365%

    No Known Activations