© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7853
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cannot" and related assertions of impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cjach
    -0.58
     full
    -0.57
     series
    -0.54
    IsMutable
    -0.54
    bcryptjs
    -0.52
     connexes
    -0.52
    unhofer
    -0.52
     TestBed
    -0.52
     pair
    -0.51
     often
    -0.51
    POSITIVE LOGITS
     Lying
    0.80
     lying
    0.77
     Tacitus
    0.74
     Evita
    0.72
     decora
    0.70
     cowards
    0.70
    DockStyle
    0.70
     liars
    0.69
     superstitions
    0.68
     heretics
    0.68
    Activations Density 0.109%

    No Known Activations