© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    manipulative traits and actions in characters or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.40
    krankungen
    -0.38
    criptive
    -0.38
     spazz
    -0.37
     gesteld
    -0.36
    qual
    -0.36
    radora
    -0.36
     verantwoorde
    -0.36
     quality
    -0.35
    stanz
    -0.35
    POSITIVE LOGITS
     trick
    1.05
     cunning
    0.95
     tricks
    0.93
     manipulate
    0.81
    tricks
    0.81
     Trick
    0.80
     Tricks
    0.79
     sneaky
    0.79
     manipulation
    0.78
    Trick
    0.78
    Activations Density 0.356%

    No Known Activations