© 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. 23-GEMMASCOPE-RES-16K
    11. 15107
    Prev
    Next
    INDEX
    Explanations

    terms related to damage and destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.50
     fehl
    -0.48
     zí
    -0.47
    cydow
    -0.47
     betweenstory
    -0.47
    isco
    -0.47
    EnableWeb
    -0.47
    ்த்த
    -0.47
    Reminds
    -0.46
     lenker
    -0.46
    POSITIVE LOGITS
     damage
    3.05
     Damage
    2.64
    damage
    2.57
    Damage
    2.49
     DAMAGE
    2.42
     damages
    2.32
     damaged
    2.21
    DAMAGE
    2.06
     destruction
    1.96
     Damages
    1.96
    Activations Density 0.453%

    No Known Activations