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. 7487
    Prev
    Next
    INDEX
    Explanations

    significant encounters and connections between individuals

    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
    PyExc
    -0.62
    zzleHttp
    -0.62
    +#+
    -0.61
    [:,:,
    -0.52
    DotNetBar
    -0.50
    writerow
    -0.50
     OFDb
    -0.50
    emony
    -0.50
     oaths
    -0.49
    '__
    -0.48
    POSITIVE LOGITS
     случайно
    0.72
    discovery
    0.70
     discovered
    0.69
     discovery
    0.69
     descubrir
    0.66
    discovered
    0.66
     hasard
    0.66
     découvre
    0.64
     chanced
    0.63
     découverte
    0.62
    Activations Density 0.341%

    No Known Activations