© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8067
    Prev
    Next
    INDEX
    Explanations

    function calls and their parameters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.58
     }}$}
    -0.54
     @"";
    -0.52
    </blockquote>
    -0.50
    }}}
    -0.49
    "",
    -0.49
    "]]
    -0.48
    </i>
    -0.48
     "";
    -0.48
    }}}}
    -0.47
    POSITIVE LOGITS
    zelfde
    0.53
     Wikiseite
    0.50
    页面存档备份
    0.46
     @"/
    0.45
    которые
    0.45
    addCriterion
    0.42
    ...).
    0.40
    reicht
    0.40
    withstanding
    0.40
     hábit
    0.40
    Activations Density 0.481%

    No Known Activations