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. 10-GEMMASCOPE-RES-16K
    6. 8850
    Prev
    Next
    INDEX
    Explanations

    the presence of formatting and typesetting commands often used in LaTeX or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.95
     Elsie
    -0.84
    omeness
    -0.77
    gettime
    -0.77
    __':
    
    -0.77
    TabIndex
    -0.76
     LUMP
    -0.76
    httphttps
    -0.76
    strona
    -0.75
     Amu
    -0.74
    POSITIVE LOGITS
    </i>
    0.63
    
    0.60
    “
    0.59
    modelBuilder
    0.59
    ‘
    0.59
    raan
    0.58
    ”,
    0.58
    <u>
    0.57
     ‘
    0.56
    ”
    0.56
    Activations Density 0.085%

    No Known Activations