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. 23-GEMMASCOPE-RES-16K
    6. 12519
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to linear approximations and models

    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
    </caption>
    -0.71
    />";
    -0.70
    **)
    -0.69
    $")
    -0.68
    ³)
    -0.68
    -),
    -0.68
     $?
    -0.67
     مرئيه
    -0.66
    ",$
    -0.65
    *",
    -0.65
    POSITIVE LOGITS
    −
    0.72
    ForTesting
    0.54
    Хьажоргаш
    0.54
     ſta
    0.52
    Климат
    0.52
    ∗
    0.51
    >−
    0.50
     uſed
    0.50
     Metropolis
    0.49
     Excuse
    0.49
    Activations Density 0.689%

    No Known Activations