© 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. 4-GEMMASCOPE-RES-16K
    11. 432
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to universal applicability and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wixt
    -0.52
    lapsingToolbar
    -0.52
     للاسماء
    -0.51
    classnames
    -0.51
    TestBed
    -0.49
    Separate
    -0.49
     separates
    -0.48
     separado
    -0.48
    aliers
    -0.48
    ModelAdmin
    -0.47
    POSITIVE LOGITS
     universal
    1.58
     universelle
    1.45
     universally
    1.43
     universale
    1.42
    universal
    1.42
     universality
    1.35
     Universal
    1.22
     UNIVERSAL
    1.22
    Universal
    1.20
     widespread
    1.18
    Activations Density 0.835%

    No Known Activations