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. 14-GEMMASCOPE-RES-16K
    6. 10560
    Prev
    Next
    INDEX
    Explanations

    references to mathematical operations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.91
     ligiloj
    -0.83
    fjspx
    -0.82
     ویکی‌پدیا
    -0.80
    cokinetic
    -0.79
     kasarigan
    -0.76
    Jeografia
    -0.75
    omock
    -0.75
    Datuak
    -0.74
    참고
    -0.73
    POSITIVE LOGITS
    <eos>
    0.62
     Majefty
    0.44
    over
    0.43
    front
    0.43
    per
    0.42
    <bos>
    0.40
     tiny
    0.39
     front
    0.39
    nt
    0.38
    tras
    0.38
    Activations Density 0.333%

    No Known Activations