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. 16-GEMMASCOPE-RES-16K
    6. 13017
    Prev
    Next
    INDEX
    Explanations

    emphasis on fishing as a serious activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UniformLocation
    -0.71
     Zus
    -0.62
    AuthGuard
    -0.61
     viewDidLoad
    -0.57
     StatelessWidget
    -0.56
    出版年
    -0.55
    ballo
    -0.52
    gridx
    -0.52
    uminense
    -0.52
    abito
    -0.51
    POSITIVE LOGITS
     anglers
    0.92
     fishing
    0.91
     angler
    0.89
     fisher
    0.88
     fisherman
    0.84
    Fishing
    0.81
     fished
    0.81
     fishery
    0.78
    fishing
    0.76
     fishermen
    0.75
    Activations Density 0.117%

    No Known Activations