© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1862
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" and related phrases indicating deficiency or absence of various elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stateMutability
    -0.41
     unbeaten
    -0.40
    Tabbed
    -0.38
    XDECREF
    -0.37
     each
    -0.36
    مراجع
    -0.36
    不同
    -0.36
    GIVEREF
    -0.36
    BeginInit
    -0.36
    Dzień
    -0.36
    POSITIVE LOGITS
     adequately
    1.15
     adequate
    1.14
     sufficiently
    0.99
     sufficient
    0.95
     Adequate
    0.91
    sufficient
    0.87
     ausreich
    0.85
    ufficient
    0.85
     proper
    0.84
     Sufficient
    0.84
    Activations Density 0.864%

    No Known Activations