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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 613
    Prev
    Next
    INDEX
    Explanations

    discussions about sensitive social and racial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.58
    IntoConstraints
    -0.55
    __(/*!
    -0.55
     övers
    -0.55
    ächlich
    -0.54
     Rossa
    -0.52
     appetizer
    -0.52
    Katso
    -0.51
    وفة
    -0.51
    ERSHIP
    -0.50
    POSITIVE LOGITS
     people
    0.98
     tragedies
    0.86
     politicians
    0.83
     sadly
    0.82
     infeliz
    0.81
     purtroppo
    0.80
    Sadly
    0.79
     incidents
    0.79
     Sadly
    0.76
     parents
    0.75
    Activations Density 0.410%

    No Known Activations