© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1295
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and limitations of liability in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.85
     CreateTagHelper
    -0.79
     initComponents
    -0.78
     MainAxisSize
    -0.76
    المكان
    -0.67
    RenderAtEndOf
    -0.66
    CompleteListener
    -0.65
    ritus
    -0.62
     surla
    -0.62
    Geschiedenis
    -0.60
    POSITIVE LOGITS
     reserves
    0.52
    mette
    0.47
     AspNetCore
    0.45
     liable
    0.43
    axi
    0.43
     exp
    0.43
    amentul
    0.42
    amazonaws
    0.41
     fe
    0.41
    Катего
    0.41
    Activations Density 0.122%

    No Known Activations