© 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. 7-GEMMASCOPE-RES-16K
    11. 3085
    Prev
    Next
    INDEX
    Explanations

    variables and expressions related to mathematical functions and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.90
     Nop
    -0.79
    ist
    -0.76
     pleaſure
    -0.75
     Mitter
    -0.72
    ignty
    -0.71
    pagation
    -0.71
     actionTypes
    -0.71
     Prey
    -0.70
    ized
    -0.68
    POSITIVE LOGITS
    r
    1.00
    Xr
    0.97
     r
    0.95
    PhysRevD
    0.91
    Marshaller
    0.85
     Corso
    0.84
     InkWell
    0.78
     Manns
    0.76
     Orr
    0.76
    ibatis
    0.74
    Activations Density 0.129%

    No Known Activations