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. 13-GEMMASCOPE-RES-16K
    6. 6658
    Prev
    Next
    INDEX
    Explanations

    terms indicating significant findings or results in scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    la
    -0.66
    on
    -0.66
    ReusableCell
    -0.64
    dro
    -0.63
    do
    -0.63
    op
    -0.63
    Top
    -0.62
    k
    -0.61
    bra
    -0.61
    p
    -0.60
    POSITIVE LOGITS
    ificance
    1.54
    ificantly
    1.42
    ificant
    1.42
    BibitemShut
    1.30
    ^(@)
    1.15
     >=",
    1.09
     myſelf
    1.09
    __':
    
    1.07
     itſelf
    1.06
    ']))
    
    1.05
    Activations Density 0.119%

    No Known Activations