© 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. 4526
    Prev
    Next
    INDEX
    Explanations

    references to actions and their consequences

    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
     Paglinawan
    -0.93
    __':
    
    -0.91
    WireFormatLite
    -0.91
     purpoſe
    -0.88
     myſelf
    -0.82
     ―――――
    -0.81
    Autoritní
    -0.79
     Audiodateien
    -0.79
     Monfieur
    -0.79
     Diſ
    -0.79
    POSITIVE LOGITS
     in
    0.67
     
    0.67
    ,
    0.67
    ↵
    0.66
     of
    0.64
      
    0.64
     for
    0.59
     was
    0.58
     that
    0.58
     with
    0.57
    Activations Density 1.572%

    No Known Activations