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. 14-GEMMASCOPE-RES-16K
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be," indicating states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scolaires
    -0.54
     énergé
    -0.53
     démocr
    -0.52
     prato
    -0.51
    書いた
    -0.51
     encodes
    -0.50
     ברי
    -0.49
     okol
    -0.49
    sili
    -0.48
     kropp
    -0.48
    POSITIVE LOGITS
    )++;
    0.82
    utnik
    0.82
     now
    0.72
    ++]=
    0.69
    SourceChecksum
    0.69
     autorytatywna
    0.69
     currently
    0.68
     trying
    0.68
    "])
    
    0.67
     working
    0.65
    Activations Density 0.182%

    No Known Activations