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. 8-GEMMASCOPE-RES-16K
    6. 8787
    Prev
    Next
    INDEX
    Explanations

    references to the sky and its various characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.88
     Canaria
    -0.72
     MDC
    -0.70
    ANNES
    -0.68
     Gabor
    -0.68
    ✨:
    -0.67
    Pinch
    -0.67
     Quince
    -0.67
    PostInfinity
    -0.67
    UDC
    -0.67
    POSITIVE LOGITS
     Sky
    1.87
    Sky
    1.84
     sky
    1.81
     SKY
    1.81
     skies
    1.56
    sky
    1.53
    SKY
    1.50
     Skies
    1.43
     skys
    1.40
     Skys
    1.33
    Activations Density 0.039%

    No Known Activations