© 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. 15064
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to the relationship between actions, conditions, and outcomes

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

    Following "as" or "exactly"

    np_acts-logits-general · gemini-2.0-flash

    exactly as prescribed or expected

    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
     <<<<<<<<<<<<<<
    -0.73
    ScopeManager
    -0.63
    SequentialGroup
    -0.59
     resourceCulture
    -0.55
     كومونز
    -0.54
     Numerade
    -0.52
     Normdatei
    -0.51
     المعيارى
    -0.49
    jspx
    -0.47
    šinou
    -0.47
    POSITIVE LOGITS
     exactly
    1.26
     zoals
    1.26
     how
    1.18
    exactly
    1.11
     EXACTLY
    1.09
     Exactly
    1.06
     ahogy
    1.04
    Exactly
    1.03
     όπως
    1.01
    how
    0.99
    Activations Density 0.290%

    No Known Activations