© 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. 10-GEMMASCOPE-RES-16K
    11. 4826
    Prev
    Next
    INDEX
    Explanations

    elements related to fundamental objections and arguments against established beliefs or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.68
     nossas
    -0.62
     our
    -0.58
     birbir
    -0.55
     mūsų
    -0.55
     nossos
    -0.53
    กัน
    -0.52
     noastre
    -0.51
     montanha
    -0.51
     unsere
    -0.50
    POSITIVE LOGITS
     himself
    1.18
    himself
    0.93
    Notae
    0.74
     herself
    0.72
     NSCoder
    0.67
    ">//
    0.65
     Himself
    0.65
     his
    0.62
    úrese
    0.60
     متعلقه
    0.58
    Activations Density 0.686%

    No Known Activations