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. 12-GEMMASCOPE-RES-16K
    6. 11606
    Prev
    Next
    INDEX
    Explanations

    references to data sources or origins in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.98
     Reſ
    -0.80
     cartier
    -0.80
     Maori
    -0.80
     Houſe
    -0.78
     Bastille
    -0.76
     CMY
    -0.75
     IMEI
    -0.75
     Whig
    -0.75
     Viceroy
    -0.74
    POSITIVE LOGITS
     FROM
    1.77
    FROM
    1.67
     From
    1.49
     from
    1.47
    from
    1.36
    From
    1.32
    Từ
    1.28
    getFrom
    1.23
     Từ
    1.20
     từ
    1.13
    Activations Density 0.252%

    No Known Activations