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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5741
    Prev
    Next
    INDEX
    Explanations

    content related to public observations and community events

    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
    thermo
    -0.49
     thermo
    -0.46
     OnInit
    -0.45
    tegra
    -0.44
    Населення
    -0.44
    исленность
    -0.44
     vestibule
    -0.43
    surveys
    -0.43
     sẻ
    -0.42
    owice
    -0.42
    POSITIVE LOGITS
     watching
    0.82
     Watching
    0.79
    Watching
    0.78
     watched
    0.73
    watching
    0.69
     watch
    0.65
     witnessing
    0.65
     witnessed
    0.64
     spectator
    0.62
     watches
    0.61
    Activations Density 0.246%

    No Known Activations