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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5908
    Prev
    Next
    INDEX
    Explanations

    elements related to phonetics and morphology in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.57
    naeus
    -0.55
     traduce
    -0.51
    eclampsia
    -0.49
     BrowserModule
    -0.48
    Scale
    -0.47
     alab
    -0.47
     anſ
    -0.47
     defire
    -0.47
     poffe
    -0.47
    POSITIVE LOGITS
     sounds
    0.90
     sound
    0.89
    RegressionTest
    0.84
     vowel
    0.78
     consonant
    0.76
     Sounds
    0.75
     consonants
    0.75
     sounded
    0.75
     sonido
    0.73
    sound
    0.72
    Activations Density 0.166%

    No Known Activations