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. 320
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal drug possession and trafficking

    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
    tagext
    -0.54
     AssemblyCulture
    -0.53
    DatabaseError
    -0.53
    authier
    -0.49
    onets
    -0.49
    ंदीखरीदारी
    -0.48
    Prot
    -0.48
    drawiam
    -0.47
    spesies
    -0.47
    getMenuInflater
    -0.46
    POSITIVE LOGITS
     drug
    1.85
     drugs
    1.77
    drug
    1.63
     Drug
    1.57
     Drugs
    1.51
     cocaine
    1.51
    drugs
    1.51
    Drug
    1.50
    Drugs
    1.45
     DRUG
    1.37
    Activations Density 0.364%

    No Known Activations