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. 12195
    Prev
    Next
    INDEX
    Explanations

    time-related measurements and financial figures

    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
     of
    -0.67
     is
    -0.55
     to
    -0.49
     with
    -0.47
     riconos
    -0.45
     frère
    -0.44
     should
    -0.44
     while
    -0.43
     in
    -0.43
     rius
    -0.42
    POSITIVE LOGITS
    NUMX
    1.37
     pleaſure
    1.17
    ^(@)
    1.13
     faſt
    1.12
     ſmall
    1.09
     houſe
    1.08
     purpoſe
    1.06
     $_"
    1.04
    '},
    
    1.02
    )";
    
    1.00
    Activations Density 0.235%

    No Known Activations