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. 5-GEMMASCOPE-RES-16K
    6. 1986
    Prev
    Next
    INDEX
    Explanations

    statements expressing strong opinions or feelings about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.81
     lenker
    -0.81
     pleaſure
    -0.77
    存于互联网档案馆
    -0.75
    IsMutable
    -0.74
    ſelves
    -0.74
    ſelf
    -0.72
     myſelf
    -0.71
    Παραπομπές
    -0.70
    Vidite
    -0.70
    POSITIVE LOGITS
     sincerely
    0.63
     sincere
    0.56
     really
    0.56
    seriously
    0.53
     seriously
    0.52
     sincer
    0.52
    Really
    0.51
     genuinely
    0.50
    really
    0.50
    incere
    0.49
    Activations Density 0.126%

    No Known Activations