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. 16-GEMMASCOPE-RES-16K
    6. 12069
    Prev
    Next
    INDEX
    Explanations

    references to illegal financial activities and regulations related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "illegal" or "in"

    np_acts-logits-general · gemini-2.0-flash

    illegal activities and inappropriate terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.60
    AndEndTag
    -0.56
    Diweddarwch
    -0.54
    utiny
    -0.52
     مرئيه
    -0.52
    rzej
    -0.51
     ivelany
    -0.50
    featureID
    -0.50
     Wiktionnaire
    -0.49
    Traducción
    -0.49
    POSITIVE LOGITS
    IBOutlet
    0.55
    Parcelize
    0.54
    ResumeLayout
    0.53
    WireFormat
    0.52
    ChatColor
    0.52
    UnknownFields
    0.51
    UrlResolution
    0.50
     transfieras
    0.50
    IBAction
    0.49
    RectangleBorder
    0.48
    Activations Density 0.350%

    No Known Activations