© 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. 14102
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to getter and setter methods for properties

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

    `set` followed by open curly brace

    np_acts-logits-general · gemini-2.0-flash

    setting values

    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
    RenderAtEndOf
    -0.78
    ViewImports
    -0.77
    RUnlock
    -0.76
    TabView
    -0.69
    ToScroll
    -0.69
    InSection
    -0.64
     JpaRepository
    -0.64
     AssemblyTitle
    -0.63
    OrNil
    -0.62
     Monfieur
    -0.62
    POSITIVE LOGITS
    ConstraintMaker
    0.78
     newValue
    0.56
    newValue
    0.52
    évaluateur
    0.47
    Changing
    0.46
     value
    0.46
    يمة
    0.45
     changing
    0.44
     rumores
    0.43
    nmgp
    0.43
    Activations Density 0.074%

    No Known Activations