Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3431
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting and structures within equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.62
    DockStyle
    -0.57
     AppCompatTheme
    -0.56
     للمعارف
    -0.54
     оригіналу
    -0.54
    #+#
    -0.53
    NameInMap
    -0.53
    GEBURTSDATUM
    -0.51
    expandindo
    -0.50
    Autoritní
    -0.50
    POSITIVE LOGITS
    \{\\
    1.01
    aligned
    0.68
    eqnarray
    0.55
    mtable
    0.54
    multline
    0.54
    align
    0.47
    Aligned
    0.47
    Personendaten
    0.45
     <<<<<<<<<<<<<<
    0.45
    complexContent
    0.41
    Activations Density 0.356%

    No Known Activations