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. 10-GEMMASCOPE-RES-16K
    6. 13154
    Prev
    Next
    INDEX
    Explanations

    specific references to investigations or inquiries regarding a subject or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daß
    -1.18
     läßt
    -1.08
     muß
    -1.06
    ^(@)
    -1.05
    (;;)
    -1.04
     ]
    
    -1.03
     Daß
    -1.02
     offenbar
    -1.00
     auffi
    -0.98
     müßte
    -0.97
    POSITIVE LOGITS
    Lastly
    0.74
     Lastly
    0.73
     specifik
    0.72
     utilizing
    0.72
    Anyways
    0.71
    Alright
    0.71
     
    0.70
     advancements
    0.70
     aforementioned
    0.69
     showcasing
    0.69
    Activations Density 4.336%

    No Known Activations