© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15187
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate evaluation or consideration of evidence in context

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

    "In the" or associated with "context."

    np_acts-logits-general · gemini-2.0-flash

    in context or perspective

    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
    AndEndTag
    -0.69
    ddots
    -0.62
    ReusableCell
    -0.60
     AssemblyVersion
    -0.58
    IonicModule
    -0.56
    unknownFields
    -0.53
    ktop
    -0.52
    machte
    -0.50
    APPE
    -0.50
    :✨
    -0.50
    POSITIVE LOGITS
     context
    2.01
    context
    1.73
     Context
    1.63
     contexto
    1.58
     CONTEXT
    1.52
    Context
    1.47
     perspective
    1.43
     contexte
    1.43
     contex
    1.38
     контек
    1.37
    Activations Density 0.414%

    No Known Activations