© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8820
    Prev
    Next
    INDEX
    Explanations

    special formatting or distinct separators within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.69
     Süß
    -0.66
    Abitanti
    -0.66
       
    -0.65
     itſelf
    -0.64
    habits
    -0.64
    FunctionFlags
    -0.62
     existence
    -0.61
     fubject
    -0.61
     mList
    -0.60
    POSITIVE LOGITS
     gets
    1.09
     get
    1.00
     Gets
    0.99
     receives
    0.98
    Gets
    0.95
     receive
    0.92
     got
    0.92
     received
    0.91
     recibe
    0.90
     Receive
    0.90
    Activations Density 0.282%

    No Known Activations