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. 8887
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and calculations related to integers

    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
     للمعارف
    -0.77
     autorytatywna
    -0.73
    PhysRevD
    -0.67
     kasarigan
    -0.67
    WriteBarrier
    -0.64
     jScrollPane
    -0.63
    SBATCH
    -0.62
     يتيمه
    -0.60
    AxisAlignment
    -0.59
    rungsseite
    -0.59
    POSITIVE LOGITS
    frac
    1.12
    <strong>
    0.62
     frac
    0.56
    ‌ی
    0.47
    ciato
    0.46
    TagMode
    0.46
    LEncoder
    0.43
    dfrac
    0.43
    noaa
    0.43
     Zjednoc
    0.43
    Activations Density 0.522%

    No Known Activations