© 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. 14-GEMMASCOPE-RES-16K
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and cellular functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.86
    ---*/
    -0.76
    PerformLayout
    -0.76
     XCTest
    -0.70
    ymce
    -0.68
     Dostupné
    -0.65
    Diwedd
    -0.65
     *__
    -0.65
     FormsModule
    -0.64
     Vero
    -0.63
    POSITIVE LOGITS
    ggg
    1.08
    gg
    1.07
     Kag
    1.05
    ging
    1.04
    gag
    1.04
     Cag
    1.02
    sag
    1.00
    ag
    1.00
    gging
    0.99
     Wag
    0.98
    Activations Density 1.072%

    No Known Activations