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. 7-GEMMASCOPE-RES-16K
    6. 8852
    Prev
    Next
    INDEX
    Explanations

    terms related to image processing and memory management in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.84
     defaultstate
    -0.84
    ExtendWith
    -0.81
    setupUi
    -0.80
     propOrder
    -0.75
    قایناق‌لار
    -0.73
    yntaxException
    -0.73
    yně
    -0.71
     JpaRepository
    -0.70
    SuccessListener
    -0.69
    POSITIVE LOGITS
    Bitmap
    2.40
     Bitmap
    2.11
     bitmap
    1.63
    bitmap
    1.48
    BITMAP
    1.11
    setImageBitmap
    1.01
    bmp
    0.95
    BitmapFactory
    0.91
     bmp
    0.88
    Bmp
    0.85
    Activations Density 0.017%

    No Known Activations