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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 4201
    Prev
    Next
    INDEX
    Explanations

    instances of legal actions and criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.91
    Życiorys
    -0.64
     kasarigan
    -0.58
     ***!
    -0.58
    期刊论文
    -0.57
    السكان
    -0.54
    солю
    -0.51
    hdysval
    -0.51
    thylamine
    -0.50
    DataSnapshot
    -0.50
    POSITIVE LOGITS
     charged
    0.82
     arrested
    0.69
     busted
    0.68
     Charged
    0.67
     indicted
    0.63
     convicted
    0.61
     فريبيس
    0.60
    AddHtmlAttribute
    0.60
     OnInit
    0.58
     arraigned
    0.58
    Activations Density 0.390%

    No Known Activations