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. 17-GEMMASCOPE-RES-16K
    6. 13316
    Prev
    Next
    INDEX
    Explanations

    various types of brackets and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bowiem
    -0.56
     totiž
    -0.51
     disponibilités
    -0.47
     nemlig
    -0.46
     volna
    -0.45
    inginan
    -0.44
    mampuan
    -0.44
    hadiran
    -0.42
    Pues
    -0.42
    wną
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.96
     متعلقه
    0.87
    OGND
    0.87
    Geplaatst
    0.86
     Only
    0.74
     only
    0.73
    interopRequire
    0.72
     pinulongan
    0.71
    +#+#
    0.71
     intptr
    0.70
    Activations Density 0.343%

    No Known Activations