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 - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2178
    Prev
    Next
    INDEX
    Explanations

    references to institutions or organizations involved in college and university settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whom
    -0.62
     Wicidata
    -0.61
     reappear
    -0.59
     élevées
    -0.58
     culturelles
    -0.56
     disappearing
    -0.56
     disappear
    -0.55
    Appear
    -0.53
     vanish
    -0.53
    principalColumn
    -0.53
    POSITIVE LOGITS
     staff
    0.96
     hopes
    0.89
     expects
    0.88
     officials
    0.85
     intends
    0.83
     plans
    0.81
     has
    0.81
     believes
    0.79
     employees
    0.78
     wants
    0.76
    Activations Density 0.571%

    No Known Activations