Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2627
    Prev
    Next
    INDEX
    Explanations

    themes related to rebellion and defiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.60
    (!__
    -0.53
     empleos
    -0.52
     immobilier
    -0.51
     pratiquer
    -0.51
     hyö
    -0.50
    DockStyle
    -0.50
     médicale
    -0.50
     virke
    -0.50
     rę
    -0.49
    POSITIVE LOGITS
     rebellious
    1.36
     disobedience
    1.21
     rebellion
    1.20
     rebel
    1.19
    rebel
    1.11
     Rebel
    1.09
     rebels
    1.06
    Rebel
    1.06
     defiance
    1.06
     mischievous
    1.01
    Activations Density 0.362%

    No Known Activations