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. 62295
    Prev
    Next
    INDEX
    Explanations

    terms related to stability and stability-related concepts

    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_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
    ers
    -0.48
    ersch
    -0.48
    outh
    -0.48
     Phương
    -0.48
     you
    -0.46
    getAs
    -0.46
     mày
    -0.46
    ery
    -0.45
    toCharArray
    -0.45
     ROY
    -0.45
    POSITIVE LOGITS
    Stable
    1.05
     Stable
    1.03
     Stability
    0.95
     stable
    0.94
     stabile
    0.94
    Stability
    0.93
     stabil
    0.93
     stabilize
    0.92
     stability
    0.90
     STABILITY
    0.90
    Activations Density 0.022%

    No Known Activations