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. 10-GEMMASCOPE-RES-16K
    6. 13221
    Prev
    Next
    INDEX
    Explanations

    terms related to brightness or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -1.04
     AppBundle
    -1.00
    TemporalType
    -0.99
     Cowan
    -0.98
    CrossRef
    -0.86
    MigrationBuilder
    -0.80
    principalColumn
    -0.78
    Geplaatst
    -0.77
    +#+
    -0.77
    PerformLayout
    -0.76
    POSITIVE LOGITS
    Sight
    1.24
    sight
    1.22
     Sight
    1.17
    IGHT
    1.02
     sight
    0.97
    sights
    0.93
     Wight
    0.87
    lights
    0.85
     Fright
    0.84
     pleaſure
    0.84
    Activations Density 0.087%

    No Known Activations