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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53310
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court motions and procedures

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

    own motion or reviews complaints

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Мексичка
    -0.78
     насељу
    -0.63
    Personensuche
    -0.63
    mappedBy
    -0.60
    béco
    -0.59
    IndentedString
    -0.58
    hoeddwyd
    -0.57
    mybatisplus
    -0.55
    SharedCtor
    -0.55
    UAWEI
    -0.54
    POSITIVE LOGITS
     complaints
    0.80
     complaint
    0.77
     Complaints
    0.75
     Complaint
    0.69
    complaint
    0.65
    Complaints
    0.65
    Complaint
    0.65
     complains
    0.59
     requests
    0.57
     concern
    0.55
    Activations Density 0.272%

    No Known Activations