© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 686
    Prev
    Next
    INDEX
    Explanations

    themes related to dishonesty and deceitful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to deception, dishonesty, or infidelity.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.56
    RectangleBorder
    -0.54
    rrggbb
    -0.47
     Савезне
    -0.46
     Мексичка
    -0.45
     surla
    -0.45
    bernate
    -0.44
     protoimpl
    -0.43
    rungsseite
    -0.43
    entador
    -0.42
    POSITIVE LOGITS
     cheating
    2.13
     cheat
    2.00
     cheats
    1.83
     cheated
    1.80
    cheat
    1.63
     Cheat
    1.50
    Cheat
    1.41
     che
    1.32
     Che
    1.27
     CHE
    1.16
    Activations Density 0.202%

    No Known Activations