© 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. 25-GEMMASCOPE-RES-16K
    6. 2841
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural phenomena and atmospheric conditions related to celestial events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.55
    Ārējās
    -0.52
     fleas
    -0.51
     ListNode
    -0.50
    Спасылкі
    -0.50
    TacToe
    -0.49
    ContentAlignment
    -0.49
    AccessFile
    -0.48
     newOwner
    -0.47
    ostomy
    -0.47
    POSITIVE LOGITS
     clouds
    1.28
     cloud
    1.25
     Cloud
    0.94
    cloud
    0.94
     CLOUD
    0.90
    clouds
    0.90
     Clouds
    0.89
     haze
    0.88
     sky
    0.87
    Cloud
    0.87
    Activations Density 0.293%

    No Known Activations