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. 11-GEMMASCOPE-RES-16K
    6. 14097
    Prev
    Next
    INDEX
    Explanations

    themes related to criticism and social recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')):
    -0.75
    دانشنامهٔ
    -0.72
    migrationBuilder
    -0.64
    typeorm
    -0.63
    '])){
    
    -0.63
    fjspx
    -0.61
     kaarangay
    -0.60
    '):
    
    -0.60
    الحياه
    -0.60
    ()]);
    -0.59
    POSITIVE LOGITS
     denen
    0.51
    ándalo
    0.49
     internazionale
    0.49
     kysy
    0.48
     afuera
    0.45
    enderror
    0.45
    ardom
    0.45
     universel
    0.45
    tvguidetime
    0.44
     zewnętrzne
    0.43
    Activations Density 0.383%

    No Known Activations