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. 17-GEMMASCOPE-RES-16K
    6. 9007
    Prev
    Next
    INDEX
    Explanations

    technical terms and commands related to programming languages, particularly in the realm of typesetting and document preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Клуб
    -0.55
     δημο
    -0.54
    oprot
    -0.54
     }}"></
    -0.54
    toms
    -0.53
    pley
    -0.51
    idste
    -0.50
    uzzi
    -0.49
     mű
    -0.49
    hips
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.83
    AddTagHelper
    0.81
    usepackage
    0.72
    WindowConstants
    0.67
    UserScript
    0.67
    Попис
    0.63
    setupUi
    0.63
    Geplaatst
    0.61
    protoimpl
    0.61
     AssemblyCulture
    0.61
    Activations Density 0.022%

    No Known Activations