© 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. 31-GEMMASCOPE-RES-16K
    11. 6568
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to assurance and ensuring that needs are met

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

    phrases expressing assurance or certainty that something will be done or achieved.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Probably
    -0.60
     probably
    -0.57
    probably
    -0.56
    SequentialGroup
    -0.56
    Probably
    -0.54
     niestety
    -0.54
     probablemente
    -0.52
     provavelmente
    -0.52
    stateMutability
    -0.51
     sometimes
    -0.50
    POSITIVE LOGITS
     properly
    0.97
     adequately
    0.89
     correctly
    0.82
    properly
    0.77
     adequate
    0.75
     sufficiently
    0.74
     Properly
    0.73
     proper
    0.69
     accurately
    0.69
    Proper
    0.68
    Activations Density 0.533%

    No Known Activations