© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7809
    Prev
    Next
    INDEX
    Explanations

    auditory stimuli and sound descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.67
    AccessFile
    -0.58
     يتيمه
    -0.49
     utafitiHapana
    -0.48
     Allociné
    -0.48
    期刊论文
    -0.47
     Normdatei
    -0.47
     للمعارف
    -0.47
    AsUp
    -0.47
    tuce
    -0.46
    POSITIVE LOGITS
     sound
    1.94
     sounds
    1.92
     noises
    1.69
     loud
    1.68
     SOUND
    1.67
     noise
    1.67
    sound
    1.66
     sounded
    1.62
    sounds
    1.62
     voice
    1.55
    Activations Density 0.470%

    No Known Activations