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. 16-GEMMASCOPE-RES-16K
    6. 6520
    Prev
    Next
    INDEX
    Explanations

    fragments of code and programming constructs related to Android development

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

    File paths and code imports

    np_acts-logits-general · gemini-2.0-flash

    code entry points and imports

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    enumi
    -0.77
     jScrollPane
    -0.62
     المعيارى
    -0.62
     HasFactory
    -0.61
    Autoritní
    -0.60
    الحياه
    -0.57
     Reverso
    -0.55
    Xna
    -0.55
     MyBatis
    -0.55
     дописавши
    -0.55
    POSITIVE LOGITS
    UnknownFieldSet
    0.61
    haupt
    0.56
    PrototypeOf
    0.51
     main
    0.51
    ANTLR
    0.50
    的主
    0.49
     مواليد
    0.46
     主
    0.46
     kurios
    0.45
    Welcome
    0.45
    Activations Density 0.039%

    No Known Activations