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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 992
    Prev
    Next
    INDEX
    Explanations

    references to damage and its implications in various contexts

    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
     autorytatywna
    -0.75
    MLLoader
    -0.73
     CreateTagHelper
    -0.73
     referenties
    -0.68
     getGroup
    -0.66
     vouloir
    -0.63
    tshire
    -0.63
    edoc
    -0.63
     betweenstory
    -0.61
    Према
    -0.60
    POSITIVE LOGITS
     damage
    3.19
     Damage
    2.99
    damage
    2.82
    Damage
    2.80
     DAMAGE
    2.80
     damages
    2.70
     Damages
    2.52
    DAMAGE
    2.26
     DAMAGES
    2.19
     damaged
    2.17
    Activations Density 0.059%

    No Known Activations