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. 6-GEMMASCOPE-RES-16K
    6. 5392
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty and doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brahmin
    -0.67
    cagon
    -0.65
    ủi
    -0.65
     Sardin
    -0.64
     Assyrian
    -0.64
     IAAF
    -0.60
     Abidjan
    -0.60
     fausse
    -0.59
     canst
    -0.59
     Basing
    -0.58
    POSITIVE LOGITS
    oubtedly
    0.86
     Réponses
    0.77
     Undoubtedly
    0.77
     undoubtedly
    0.65
     NDEBUG
    0.56
    ništvo
    0.53
    edly
    0.53
    adto
    0.51
    AnimationsModule
    0.51
     benar
    0.50
    Activations Density 0.120%

    No Known Activations