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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29
    Prev
    Next
    INDEX
    Explanations

    calls to action and promotion-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases urging immediate action or contact, often with urgency or promotional context.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
    sätzlich
    -0.61
    ">@
    -0.56
     PyTuple
    -0.51
    ]=>
    -0.50
    ThemeOverlay
    -0.50
    WebElementEntity
    -0.50
    ).*
    -0.50
    generally
    -0.49
     Мексичка
    -0.49
     decently
    -0.49
    POSITIVE LOGITS
     виправивши
    0.64
     ISNI
    0.60
    raszamy
    0.59
    buttonBar
    0.56
    Autoritní
    0.55
     jurídico
    0.54
     Paglinawan
    0.54
    yelidikan
    0.54
     aventure
    0.54
     متعلقه
    0.53
    Activations Density 0.090%

    No Known Activations