© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "analysis" and related phrases

    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
    足
    -0.68
    덟
    -0.67
    Ordinal
    -0.62
    Poppins
    -0.60
     defaultstate
    -0.59
    Sock
    -0.58
     méri
    -0.58
    希望
    -0.58
    HOP
    -0.58
     HOP
    -0.58
    POSITIVE LOGITS
     analyses
    2.23
     analysis
    2.19
     Analyses
    2.11
     Analysis
    2.02
     ANALYSIS
    1.98
    ANALYSIS
    1.96
    analysis
    1.93
    Analyses
    1.92
     analys
    1.88
    analyses
    1.86
    Activations Density 0.080%

    No Known Activations