© 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. 8-GEMMASCOPE-RES-16K
    11. 8943
    Prev
    Next
    INDEX
    Explanations

    themes related to disguise and infiltration

    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
    fetchone
    -0.54
     penghar
    -0.50
     commerciales
    -0.48
    🚲
    -0.47
    VersionUID
    -0.47
    تفصیلات
    -0.46
    Geometry
    -0.46
     Optik
    -0.46
    comet
    -0.45
    Wirtschaft
    -0.45
    POSITIVE LOGITS
     imperson
    0.76
     disguise
    0.69
     disgu
    0.64
    下载附件
    0.64
     imitating
    0.63
     chameleon
    0.63
     costumes
    0.62
    
    0.61
    LookAnd
    0.60
     Shakspeare
    0.59
    Activations Density 0.258%

    No Known Activations