© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5264
    Prev
    Next
    INDEX
    Explanations

    the term "ban" and its variations related to prohibitions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    Dina
    -0.61
     fasc
    -0.59
    son
    -0.56
     Storey
    -0.56
     vů
    -0.55
     delin
    -0.55
     carc
    -0.54
     storie
    -0.54
     بيها
    -0.53
    c
    -0.52
    POSITIVE LOGITS
     ban
    2.70
     Ban
    2.38
    Ban
    2.24
     bans
    2.10
     banning
    1.89
     banned
    1.86
    ban
    1.82
     BAN
    1.80
     Bans
    1.70
    BAN
    1.68
    Activations Density 0.056%

    No Known Activations