© 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. 11-GEMMASCOPE-RES-16K
    11. 3969
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and threats in a context of power and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.60
    اعمال
    -0.50
    Xna
    -0.50
    heil
    -0.47
    zijn
    -0.45
    brokes
    -0.45
    daje
    -0.45
    observers
    -0.45
     doPost
    -0.44
    hláš
    -0.44
    POSITIVE LOGITS
     persuasive
    0.79
     convincing
    0.78
     arguments
    0.76
     convinces
    0.74
    enumi
    0.72
     convince
    0.71
     argument
    0.71
     blackmail
    0.70
     persuasion
    0.69
     argumento
    0.68
    Activations Density 0.413%

    No Known Activations