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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2058
    Prev
    Next
    INDEX
    Explanations

    terms related to bans and prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.78
    p
    -0.70
    mtext
    -0.68
    ณะ
    -0.59
    )}</
    -0.59
     }}"></
    -0.59
    mes
    -0.59
    tagext
    -0.58
    ":[{
    -0.57
    </em>
    -0.56
    POSITIVE LOGITS
     bans
    1.45
     banning
    1.41
     banned
    1.38
     Bans
    1.27
     prohibitions
    1.23
    Bans
    1.23
     prohibition
    1.22
     prohibiting
    1.21
     prohibit
    1.20
    banned
    1.14
    Activations Density 0.188%

    No Known Activations