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. 23-GEMMASCOPE-RES-16K
    6. 6406
    Prev
    Next
    INDEX
    Explanations

    phrases related to cellular networks and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.63
     statute
    -0.58
    WindowConstants
    -0.58
    urlencoded
    -0.56
    glEnd
    -0.54
    conference
    -0.54
    зулта
    -0.52
    kover
    -0.52
    TintMode
    -0.52
    JKLM
    -0.51
    POSITIVE LOGITS
     cell
    4.23
    cell
    3.77
     Cell
    3.58
    Cell
    3.39
     CELL
    3.21
    CELL
    2.89
     cells
    2.82
     cellule
    2.47
    cells
    2.45
     Cells
    2.43
    Activations Density 0.469%

    No Known Activations