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. 2-GEMMASCOPE-RES-16K
    6. 2231
    Prev
    Next
    INDEX
    Explanations

    references to table cells in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.69
    TintMode
    -0.63
    Grady
    -0.55
     Conference
    -0.54
    nologue
    -0.54
    itous
    -0.53
     Roskov
    -0.53
    MODO
    -0.51
     Drapeau
    -0.50
    ropical
    -0.49
    POSITIVE LOGITS
    cell
    2.16
    CELL
    2.06
    Cell
    2.04
     CELL
    1.99
     Cell
    1.96
     cell
    1.83
    cells
    1.74
    Cells
    1.70
     Cells
    1.59
     cells
    1.55
    Activations Density 0.245%

    No Known Activations