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. 33-GEMMASCOPE-RES-131K
    6. 65865
    Prev
    Next
    INDEX
    Explanations

    programming constructs and control flow elements

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increase
    -0.70
    increase
    -0.68
     increases
    -0.68
     aumento
    -0.67
    Increases
    -0.66
     Increase
    -0.65
     Increases
    -0.65
     (++
    -0.65
    Increase
    -0.64
    increases
    -0.63
    POSITIVE LOGITS
     decreasing
    1.52
     decrease
    1.50
     reduction
    1.44
     reductions
    1.40
     decreases
    1.39
     decreased
    1.31
     decrement
    1.31
     reduced
    1.31
     reduce
    1.30
     Decrease
    1.29
    Activations Density 0.026%

    No Known Activations