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-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23175
    Prev
    Next
    INDEX
    Explanations

    references to data structures and fields in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _))
    -0.35
     empleos
    -0.35
     []),
    -0.34
    '},
    
    -0.33
    >");
    
    -0.32
    /$',
    -0.32
     invokingState
    -0.31
     ammat
    -0.31
    }\]
    -0.31
     ""),
    -0.31
    POSITIVE LOGITS
     Infórmanos
    0.63
    featureID
    0.62
     transfieras
    0.61
     ویکی‌پدی
    0.56
    encodeWith
    0.54
    
    0.54
    pylene
    0.52
    -------------</
    0.51
    KommentareTeilen
    0.51
    ########.
    0.50
    Activations Density 0.008%

    No Known Activations