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. 2-GEMMASCOPE-RES-16K
    6. 4725
    Prev
    Next
    INDEX
    Explanations

    technical language and phrases related to systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nameof
    -0.47
    EndInit
    -0.45
     Réponses
    -0.44
     Ouv
    -0.43
     XHTML
    -0.42
     EG
    -0.42
    DidLoad
    -0.42
     videre
    -0.42
    exitRule
    -0.42
     않
    -0.41
    POSITIVE LOGITS
    kháu
    0.85
    qrstuvwxyz
    0.81
     surla
    0.75
    UnsafeEnabled
    0.73
     חיצוניים
    0.72
    OGND
    0.71
     AssemblyVersion
    0.71
    AutoresizingMask
    0.68
    Geplaatst
    0.67
     nakalista
    0.66
    Activations Density 2.552%

    No Known Activations