Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 8926
    Prev
    Next
    INDEX
    Explanations

    transitions or conclusions in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.61
    ſelves
    -0.59
    
    -0.53
    */)
    -0.53
    ாள
    -0.52
     الحره
    -0.52
     ete
    -0.51
    }")
    
    -0.51
    aarrggbb
    -0.50
     soe
    -0.50
    POSITIVE LOGITS
     yeah
    1.11
     yes
    1.03
     how
    0.93
     what
    0.90
     far
    0.89
    oner
    0.88
     why
    0.87
     if
    0.86
     basically
    0.83
     imagine
    0.75
    Activations Density 0.068%

    No Known Activations