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. 15-GEMMASCOPE-RES-16K
    6. 2406
    Prev
    Next
    INDEX
    Explanations

    expressions related to arguments, claims, and the act of reasoning or discussing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gog
    -0.51
    这个问题
    -0.50
     belong
    -0.49
     appartient
    -0.49
     belongs
    -0.49
    出来了
    -0.49
     Überblick
    -0.47
    RetentionPolicy
    -0.47
     '*')
    -0.47
     questione
    -0.47
    POSITIVE LOGITS
     հղումներ
    0.81
    __':
    
    0.76
    thâu
    0.75
    OGND
    0.71
     кӀ
    0.71
     perhaps
    0.71
    IsMutable
    0.68
    Dtor
    0.67
    __":
    
    0.67
     }}$}
    0.67
    Activations Density 0.618%

    No Known Activations