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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9608
    Prev
    Next
    INDEX
    Explanations

    specific informational content and promotional elements related to online banking and financial services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ponses
    -0.57
    orianCalendar
    -0.54
    Bonsoir
    -0.48
     Italijanski
    -0.47
    Gruss
    -0.46
    فایل
    -0.46
    myspace
    -0.46
    Identyfik
    -0.46
    ękuję
    -0.45
     ſtre
    -0.45
    POSITIVE LOGITS
     article
    0.68
     articles
    0.57
     guides
    0.49
     guide
    0.48
    article
    0.48
     artikel
    0.48
     artikke
    0.44
    artikel
    0.44
     Article
    0.43
     artículo
    0.43
    Activations Density 0.221%

    No Known Activations