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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11756
    Prev
    Next
    INDEX
    Explanations

    assignment statements and variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     –
    -0.63
     he
    -0.62
     of
    -0.61
     ру
    -0.60
     os
    -0.60
     —
    -0.59
     nh
    -0.59
    ors
    -0.59
     Rot
    -0.59
     us
    -0.58
    POSITIVE LOGITS
     ویکی‌پدی
    1.25
     Cæsar
    1.08
     crdi
    1.05
     purpoſe
    1.04
     itſelf
    1.02
     Romains
    1.00
     Haarlem
    0.99
     pleaſure
    0.99
     houſe
    0.98
     EEU
    0.96
    Activations Density 0.493%

    No Known Activations