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. 1-GEMMASCOPE-RES-16K
    6. 13532
    Prev
    Next
    INDEX
    Explanations

    phrases related to support for artists and their development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.65
     Efq
    -1.63
    تقاوى
    -1.60
     Theſe
    -1.57
     Monfieur
    -1.56
    ſelf
    -1.56
    ^(@)
    -1.55
     itſelf
    -1.53
     kaarangay
    -1.53
    ſelves
    -1.52
    POSITIVE LOGITS
    .
    1.70
    ↵
    1.67
    </em>
    1.16
        
    1.16
      
    1.09
       
    1.06
    ↵↵↵
    1.05
    ...
    1.04
    </strong>
    1.04
    ).
    1.03
    Activations Density 12.123%

    No Known Activations