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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12897
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions related to hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organizador
    -0.53
     cardin
    -0.51
    oxone
    -0.51
     vine
    -0.50
     animato
    -0.49
    vaux
    -0.48
    lardır
    -0.48
    NOPQRST
    -0.47
     Alois
    -0.47
    uose
    -0.47
    POSITIVE LOGITS
     If
    0.96
    "):
    
    0.96
     if
    0.96
    "))
    
    0.95
     gdyby
    0.94
    إذا
    0.92
    หาก
    0.91
    ")]
    
    0.84
     إذا
    0.84
    '),
    
    0.84
    Activations Density 0.204%

    No Known Activations