© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrencies and their exchanges

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

    numerical values and scientific notation in technical code and mathematical contexts.

    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
     nahilalakip
    -0.46
    complexContent
    -0.45
    URLException
    -0.44
    MockBean
    -0.44
     Wikimedijinoj
    -0.43
    yntaxException
    -0.43
     ostavi
    -0.42
     OMITBAD
    -0.42
     BoxFit
    -0.42
     olympiques
    -0.42
    POSITIVE LOGITS
     Units
    0.63
     units
    0.63
     bitcoins
    0.55
    Units
    0.52
     unidades
    0.51
     UNITS
    0.51
     Unit
    0.50
     unités
    0.49
     BTC
    0.49
     ETH
    0.48
    Activations Density 0.176%

    No Known Activations