© 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. 11-GEMMASCOPE-RES-16K
    6. 6718
    Prev
    Next
    INDEX
    Explanations

    common first-person pronouns and phrases indicating personal action or intent

    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
     Jefus
    -1.05
     itſelf
    -1.05
     Efq
    -1.04
    IVEREF
    -1.00
    StoryboardSegue
    -0.98
     pleaſure
    -0.95
    GEBURTSDATUM
    -0.94
     Shakspeare
    -0.94
     greateſt
    -0.94
     fubject
    -0.94
    POSITIVE LOGITS
    *}\
    0.65
     use
    0.60
     far
    0.53
    [])
    
    0.51
     a
    0.50
     carefully
    0.49
    نس
    0.49
     using
    0.49
    ).\
    0.49
     previously
    0.48
    Activations Density 0.552%

    No Known Activations