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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 939
    Prev
    Next
    INDEX
    Explanations

    references to online sites and websites

    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
    LEADING
    -0.82
     bezeichneter
    -0.72
    )”
    -0.66
    ”、“
    -0.66
    SerializeField
    -0.66
     Kearney
    -0.64
     Iva
    -0.63
    ])):
    -0.63
    //
    -0.62
     Kraw
    -0.62
    POSITIVE LOGITS
     Sites
    1.93
     Site
    1.88
     SITE
    1.84
     sites
    1.80
    SITE
    1.78
     site
    1.77
     SITES
    1.71
    Site
    1.69
    Sites
    1.69
    sites
    1.61
    Activations Density 0.118%

    No Known Activations