© 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. 3-GEMMASCOPE-RES-16K
    11. 9624
    Prev
    Next
    INDEX
    Explanations

    terms associated with destruction and annihilation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.69
     Shifts
    -0.68
     TextAppearance
    -0.65
    ageo
    -0.63
     shifts
    -0.62
    Hozzáférés
    -0.60
    WidgetItem
    -0.59
     poule
    -0.59
    elizabeth
    -0.57
     mmHg
    -0.57
    POSITIVE LOGITS
     destroy
    2.53
     Destroy
    2.44
     destruction
    2.38
     destroyed
    2.36
     destroys
    2.28
     destroying
    2.25
     Destruction
    2.23
    destroy
    2.21
    Destroy
    2.13
    estroying
    2.09
    Activations Density 0.060%

    No Known Activations