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. 20-GEMMASCOPE-RES-16K
    6. 282
    Prev
    Next
    INDEX
    Explanations

    structured data or syntax patterns, particularly in programming or markup languages

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

    Code, brackets, and special characters

    np_acts-logits-general · gemini-2.0-flash

    LaTeX tables or JSON structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.64
    galus
    -0.59
    /*:
    -0.55
     blows
    -0.54
    setupUi
    -0.53
    ্দ
    -0.53
     Breslau
    -0.53
    FieldDescriptor
    -0.52
    ranath
    -0.52
    XMLSchema
    -0.52
    POSITIVE LOGITS
     beginnetje
    0.57
    ierre
    0.50
    قایناق‌لار
    0.50
    Geografi
    0.49
    annin
    0.49
     annoncé
    0.47
     extra
    0.46
     transfieras
    0.46
     tag
    0.43
    tvguidetime
    0.43
    Activations Density 0.045%

    No Known Activations