Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11139
    Prev
    Next
    INDEX
    Explanations

    words expressing certainty or affirmation

    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
     çoğu
    -0.60
    wieś
    -0.57
    oredCriteria
    -0.56
    tock
    -0.55
     stessi
    -0.55
    jspb
    -0.55
    asos
    -0.55
     sederhana
    -0.55
     avviene
    -0.54
     Houſe
    -0.52
    POSITIVE LOGITS
     definitely
    1.67
     Definitely
    1.50
    definitely
    1.44
    Definitely
    1.44
     certainly
    1.43
     surely
    1.39
     definately
    1.39
     Certainly
    1.32
    certainly
    1.28
     definite
    1.28
    Activations Density 0.191%

    No Known Activations