© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9753
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strange" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    वरण
    -0.63
    सन्दर्भ
    -0.56
    先代
    -0.54
    FTFY
    -0.53
     menang
    -0.53
    batore
    -0.52
     gainera
    -0.51
    
    -0.51
     Pollock
    -0.51
    cyklo
    -0.50
    POSITIVE LOGITS
     strange
    0.98
     weird
    0.85
    strange
    0.84
    Strange
    0.84
     odd
    0.82
    Weird
    0.82
    hoe
    0.81
    weird
    0.80
    odd
    0.77
    setopt
    0.75
    Activations Density 0.053%

    No Known Activations