Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6728
    Prev
    Next
    INDEX
    Explanations

    code elements related to method definitions and their returns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    
    -0.93
    تقاوى
    -0.73
    ConstraintMaker
    -0.68
     himo
    -0.66
     kaynağından
    -0.63
    openqa
    -0.63
    sizeCache
    -0.60
    enterOuterAlt
    -0.58
    webElementXpaths
    -0.56
    principalColumn
    -0.54
    POSITIVE LOGITS
    noinspection
    0.59
    }}/>
    0.57
    "/>
    0.53
    Kt
    0.52
    }/>
    0.51
     PhpStorm
    0.50
    =""/>
    0.46
    />,
    0.46
    Carriera
    0.46
    aroo
    0.44
    Activations Density 0.038%

    No Known Activations