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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14661
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and configurations in programming, particularly focused on defining methods and handling application settings

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

    Code-related special characters and keywords

    np_acts-logits-general · gemini-2.0-flash

    CydD

    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
     déc
    -0.48
    ifoli
    -0.48
    Vanjske
    -0.47
     PartialEq
    -0.44
     textStatus
    -0.43
    uintptr
    -0.42
     pungkasnya
    -0.41
    ViewInit
    -0.41
     śmier
    -0.41
    deinit
    -0.40
    POSITIVE LOGITS
     kaarangay
    0.97
    WithIOException
    0.88
    TypedDataSet
    0.84
    bootstrapcdn
    0.82
     kasarigan
    0.81
    StoreMessageInfo
    0.79
    +#+#
    0.79
    tagHelperRunner
    0.77
    InjectAttribute
    0.77
     EnglishChoose
    0.75
    Activations Density 0.122%

    No Known Activations