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. 8-GEMMASCOPE-RES-16K
    6. 8183
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific measurement and analysis

    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
     social
    -0.48
    οιν
    -0.46
    jší
    -0.44
     פרס
    -0.44
     inmedi
    -0.44
    yaszt
    -0.43
    yafet
    -0.43
    IActionResult
    -0.42
     payé
    -0.41
    انتهای
    -0.41
    POSITIVE LOGITS
    TagMode
    0.85
    }],
    
    0.84
    verifyException
    0.83
    ValueStyle
    0.81
    Tikang
    0.76
     @"/
    0.76
    .*")]
    0.76
    Dichloropropane
    0.73
    ]));
    
    0.73
    AddTagHelper
    0.71
    Activations Density 0.877%

    No Known Activations