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. 17-GEMMASCOPE-RES-16K
    6. 5978
    Prev
    Next
    INDEX
    Explanations

    elements of code related to defining and manipulating classes and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.78
    )";
    
    -0.76
    )");
    
    -0.76
     المعيارى
    -0.75
    '):
    
    -0.75
    tvguidetime
    -0.75
    '},
    
    -0.74
    ]='\
    -0.72
     }}$}
    -0.71
     Мексичка
    -0.70
    POSITIVE LOGITS
     ...
    1.03
    </code>
    0.94
     [...]
    0.88
     ....
    0.85
    </em>
    0.85
     ..."
    0.84
     …
    0.82
    ...
    0.81
    ....
    0.80
    //...
    0.78
    Activations Density 0.762%

    No Known Activations