© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10498
    Prev
    Next
    INDEX
    Explanations

    expressions indicating positive attitudes or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.66
     Jefus
    -0.63
    TestingModule
    -0.61
     Reſ
    -0.60
     utaf
    -0.59
    DeleteBehavior
    -0.59
     Utilizing
    -0.56
     guaranty
    -0.56
    jadinya
    -0.55
     می‌باشد
    -0.55
    POSITIVE LOGITS
    enumi
    0.66
     Incidentally
    0.63
     فريبيس
    0.61
     gainera
    0.59
    ={`/
    0.59
     الرياضيه
    0.58
     Bengaluru
    0.58
    とはいえ
    0.58
     spoilt
    0.57
    COLOUR
    0.56
    Activations Density 0.221%

    No Known Activations