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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 1419
    Prev
    Next
    INDEX
    Explanations

    phrases related to auditory perception or the act of listening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.73
    idavit
    -0.72
     Sub
    -0.70
    tieth
    -0.69
     metav
    -0.69
     ​​
    -0.68
    ErrUnexpectedEOF
    -0.68
     Produk
    -0.67
     Picchu
    -0.65
    mages
    -0.63
    POSITIVE LOGITS
     hears
    1.84
     hear
    1.77
     Hear
    1.75
     heard
    1.72
     HEAR
    1.66
    Hear
    1.59
     Heard
    1.58
    Heard
    1.54
     Hearn
    1.47
    hear
    1.42
    Activations Density 0.046%

    No Known Activations