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. 8-GEMMASCOPE-RES-16K
    6. 8504
    Prev
    Next
    INDEX
    Explanations

    the word "although" and its variations in the context of contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.97
    c
    -0.89
    y
    -0.86
    er
    -0.86
     &
    -0.83
    .
    -0.80
    ci
    -0.78
    yd
    -0.76
    en
    -0.75
    r
    -0.74
    POSITIVE LOGITS
    makeConstraints
    1.09
    BibitemShut
    1.09
    hematical
    1.09
     onCreateView
    1.07
    parsedMessage
    1.06
     defaultstate
    1.05
     Мексичка
    1.03
     doubtnut
    1.03
     nahilalakip
    1.01
     ་་
    1.01
    Activations Density 0.132%

    No Known Activations