© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7510
    Prev
    Next
    INDEX
    Explanations

    phrases related to the seriousness or significance of actions or statements

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

    expressions meaning "to consider something as obvious or unimportant" or "to accept something without question."

    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
    BeginContext
    -0.57
     betweenstory
    -0.55
    delwed
    -0.54
    iNdEx
    -0.53
    transQ
    -0.52
     Photocase
    -0.52
     مرئيه
    -0.50
    elemField
    -0.49
     Chwiliwch
    -0.49
     disambiguazione
    -0.48
    POSITIVE LOGITS
     serious
    1.51
     seriousness
    1.43
     Serious
    1.40
    serious
    1.39
     seriously
    1.37
    Serious
    1.32
     serius
    1.24
    seriously
    1.16
    Seriously
    1.11
     serio
    1.06
    Activations Density 0.224%

    No Known Activations