© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5581
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies or commissions

    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
     WaitForSeconds
    -0.88
    ValueStyle
    -0.75
    __*/
    -0.75
    Rptr
    -0.72
    TIMORE
    -0.70
    Dtor
    -0.69
    ANTAGES
    -0.67
     дописавши
    -0.65
    unyi
    -0.65
    EndTag
    -0.64
    POSITIVE LOGITS
     Commission
    2.31
     commission
    2.27
    Commission
    2.20
     commissions
    2.14
     COMMISSION
    2.14
     Commissions
    2.14
     commissioners
    1.95
    commission
    1.86
     Commissioners
    1.72
     commissioned
    1.58
    Activations Density 0.051%

    No Known Activations