© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10722
    Prev
    Next
    INDEX
    Explanations

    code structures and type checks in programming languages

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

    Code referring to types or classes

    np_acts-logits-general · gemini-2.0-flash

    checking object types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.70
    addCriterion
    -0.59
     esternos
    -0.54
    LabelTagHelper
    -0.54
    urbation
    -0.49
    HomeAsUpEnabled
    -0.47
     <=",
    -0.47
    HandlerContext
    -0.46
    rigal
    -0.46
    ennifer
    -0.45
    POSITIVE LOGITS
     type
    1.60
     types
    1.52
     species
    1.45
     TYPE
    1.36
    类型
    1.36
    type
    1.36
    TYPE
    1.28
     tipo
    1.27
     Types
    1.25
     Type
    1.24
    Activations Density 0.601%

    No Known Activations