© 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. 20-GEMMASCOPE-RES-16K
    6. 9598
    Prev
    Next
    INDEX
    Explanations

    terms related to radio stations and broadcasting

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

    radio station call signs and frequencies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     взаимо
    -0.34
    тинг
    -0.34
     Procu
    -0.32
     pade
    -0.32
     sm
    -0.32
    ροι
    -0.31
    hashCode
    -0.30
     plong
    -0.29
    JoinTable
    -0.29
    ücks
    -0.29
    POSITIVE LOGITS
     radio
    0.89
     rádio
    0.87
     broadcasters
    0.80
     broadcasting
    0.80
    radio
    0.79
     broadcast
    0.78
     broadcasts
    0.77
     Radio
    0.77
     radios
    0.76
     broadcaster
    0.74
    Activations Density 0.190%

    No Known Activations