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. 20-GEMMASCOPE-RES-131K
    6. 8088
    Prev
    Next
    INDEX
    Explanations

    elements related to predictions and analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation marks (especially periods) at sentence boundaries, often occurring with prediction statements or at paragraph transitions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.44
    transQ
    -0.43
    velles
    -0.42
    expandindo
    -0.41
    Xna
    -0.41
     TAMBÉM
    -0.41
    DECREF
    -0.40
     Савезне
    -0.40
     jPanel
    -0.39
     hemel
    -0.39
    POSITIVE LOGITS
    Prediction
    0.54
     Prediction
    0.52
    ModelSerializer
    0.51
     prediction
    0.50
    prediction
    0.49
     predicts
    0.47
    RegressionTest
    0.46
     victory
    0.46
    '}),
    0.44
     predict
    0.43
    Activations Density 0.010%

    No Known Activations