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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28123
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic papers

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

    arXiv papers

    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
    GraphicsUnit
    -0.83
    MigrationBuilder
    -0.76
    XmlAccessorType
    -0.75
     nahilalakip
    -0.74
     useRouter
    -0.72
     يتيمه
    -0.71
    richTextPanel
    -0.70
    UrlResolution
    -0.69
     rhestr
    -0.68
    pinMode
    -0.68
    POSITIVE LOGITS
    ุทธ
    0.55
    Mode
    0.49
    Pass
    0.47
    passing
    0.46
     spalle
    0.46
    mode
    0.43
    Passing
    0.43
     passing
    0.42
    arXiv
    0.42
     Feria
    0.42
    Activations Density 0.023%

    No Known Activations