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. 3-GEMMASCOPE-RES-16K
    6. 12860
    Prev
    Next
    INDEX
    Explanations

    references to diameter measurements and mentions of shopping malls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -1.00
     sight
    -0.69
     Clegg
    -0.64
     Sight
    -0.64
    casus
    -0.63
    prim
    -0.63
     dég
    -0.63
    Tru
    -0.62
    ilig
    -0.62
    ecore
    -0.62
    POSITIVE LOGITS
     elite
    0.93
     Elite
    0.87
    elite
    0.86
     Mall
    0.84
    Elite
    0.80
     elites
    0.79
     Thrust
    0.79
    PerformLayout
    0.78
    Thrust
    0.76
     mainstream
    0.75
    Activations Density 0.108%

    No Known Activations