© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28333
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to corporate values and responsibilities, particularly focusing on innovation and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.71
     nahilalakip
    -0.65
    ImageField
    -0.60
    CppMethod
    -0.59
    setViewportView
    -0.57
    protoimpl
    -0.56
    );
    -0.56
    Knows
    -0.55
     Italijani
    -0.54
    principalTable
    -0.54
    POSITIVE LOGITS
    </strong>
    0.54
     ویکی‌پدیا
    0.52
    ConstraintMaker
    0.49
     člá
    0.48
    ddots
    0.48
    jsxFileName
    0.47
    UpInside
    0.46
    ніципа
    0.46
     Hinsicht
    0.45
     ModelRenderer
    0.45
    Activations Density 0.072%

    No Known Activations