Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12648
    Prev
    Next
    INDEX
    Explanations

    the structure and components of language, specifically phonetic inventories and morphological aspects

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

    Phonetics, sounds, and pronunciation

    np_acts-logits-general · gemini-2.0-flash

    phonetic distinctions consonants vowels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scale
    -0.60
     epid
    -0.60
    cale
    -0.60
    Scale
    -0.59
     Scale
    -0.56
     VizieR
    -0.56
    scale
    -0.56
    ynie
    -0.55
    Circa
    -0.54
    |}{}
    -0.54
    POSITIVE LOGITS
     sound
    0.69
     sounds
    0.69
     consonants
    0.64
     consonant
    0.64
     vowel
    0.62
     Sounds
    0.60
     vowels
    0.59
     sonidos
    0.59
     sonido
    0.58
     vokal
    0.58
    Activations Density 0.197%

    No Known Activations