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. 12-GEMMASCOPE-RES-16K
    6. 6366
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and elements related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ånga
    -0.56
     StatefulWidget
    -0.54
    otheek
    -0.53
     doInBackground
    -0.52
    StructEnd
    -0.50
    epiece
    -0.48
    illotine
    -0.48
    følgelig
    -0.47
     برانيه
    -0.46
    ście
    -0.46
    POSITIVE LOGITS
     resourceCulture
    0.70
    ChromeDriver
    0.58
    ⓘ
    0.55
    addPreferredGap
    0.54
    ändigkeit
    0.52
     getDefault
    0.52
     dépens
    0.51
     دیکھیے
    0.51
     defaultstate
    0.50
    Begriffsklä
    0.50
    Activations Density 0.525%

    No Known Activations