© 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. 2-GEMMASCOPE-RES-16K
    11. 4270
    Prev
    Next
    INDEX
    Explanations

    terms related to deception or dishonesty

    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
     CanadaChoose
    -0.61
     Applies
    -0.49
     keny
    -0.49
     recite
    -0.47
     organise
    -0.47
     respira
    -0.47
     Proven
    -0.46
    росло
    -0.46
     invent
    -0.46
     contradict
    -0.46
    POSITIVE LOGITS
    addGap
    0.65
    protoimpl
    0.65
     dis
    0.63
     мәкал
    0.60
     kuiten
    0.58
     epä
    0.56
    AnchorStyles
    0.56
     excru
    0.56
    addPreferredGap
    0.54
    MessageTagHelper
    0.52
    Activations Density 1.925%

    No Known Activations