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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15683
    Prev
    Next
    INDEX
    Explanations

    references to legal accusations or controversies involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     prochaines
    -0.35
    Derbyniad
    -0.34
     noastră
    -0.33
     femininas
    -0.32
     is
    -0.32
     nogen
    -0.32
     tomorrow
    -0.31
     forças
    -0.29
     will
    -0.29
     exemplaires
    -0.29
    POSITIVE LOGITS
     fashiola
    0.69
    iſchen
    0.65
    ſchaft
    0.65
    iſche
    0.64
     ſchon
    0.63
    <unused43>
    0.63
    ſelben
    0.63
     zwiſchen
    0.62
     好文分享
    0.62
    <unused41>
    0.62
    Activations Density 0.813%

    No Known Activations