© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6784
    Prev
    Next
    INDEX
    Explanations

    concepts related to protection and prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detr
    -0.56
     inher
    -0.56
     piv
    -0.56
     tabl
    -0.54
     poffe
    -0.54
     sepul
    -0.53
     asc
    -0.52
     iner
    -0.52
     pref
    -0.51
     dedu
    -0.50
    POSITIVE LOGITS
     prevent
    1.26
     protect
    1.15
     undermine
    1.11
     discourage
    1.07
     preclude
    1.05
    prevent
    1.05
     minimise
    1.01
     deprive
    1.00
     mitigate
    1.00
     avoid
    0.99
    Activations Density 0.340%

    No Known Activations