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. 0-GEMMASCOPE-RES-16K
    6. 372
    Prev
    Next
    INDEX
    Explanations

    specific terms related to locations or areas described as "spots."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.62
     volna
    -0.52
    Clik
    -0.51
    volezza
    -0.50
     demografica
    -0.48
    варь
    -0.47
     Alters
    -0.47
    ages
    -0.46
     незавершена
    -0.45
     Paglinawan
    -0.45
    POSITIVE LOGITS
    Spot
    1.02
    spots
    1.01
     Spot
    1.01
    spot
    1.01
     spot
    1.01
     spots
    0.92
     SPOT
    0.90
     Spots
    0.88
    SPOT
    0.79
     spotted
    0.76
    Activations Density 0.075%

    No Known Activations