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. 10867
    Prev
    Next
    INDEX
    Explanations

    code-related structures and keywords, particularly those involving data handling and user interface 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
    -
    -0.63
     pre
    -0.56
    amate
    -0.54
    .
    -0.50
     total
    -0.49
     Pre
    -0.48
     đề
    -0.48
     x
    -0.47
     
    -0.47
    ेट
    -0.46
    POSITIVE LOGITS
    AccessorTable
    1.07
    FormTagHelper
    1.02
    </thead>
    0.94
    \{\\
    0.85
     NSCoder
    0.85
    NUMX
    0.83
     发表于
    0.79
    RectangleBorder
    0.78
    isContained
    0.78
    PullParser
    0.77
    Activations Density 0.004%

    No Known Activations