© 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. 21-GEMMASCOPE-RES-16K
    11. 9251
    Prev
    Next
    INDEX
    Explanations

    phrases related to damage and its consequences 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.57
     Fußballspieler
    -0.47
    verture
    -0.47
     fehl
    -0.46
    yntaxException
    -0.46
     smě
    -0.45
    Revenir
    -0.45
    něž
    -0.43
    isco
    -0.42
    KommentareTeilen
    -0.41
    POSITIVE LOGITS
     damage
    2.65
    damage
    2.25
     Damage
    2.21
     DAMAGE
    2.11
    Damage
    2.08
     damages
    1.97
     harm
    1.93
    DAMAGE
    1.77
     Damages
    1.65
     danni
    1.62
    Activations Density 0.370%

    No Known Activations