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. 1-GEMMASCOPE-RES-16K
    6. 2712
    Prev
    Next
    INDEX
    Explanations

    mentions of the Internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.49
    ApplicationTests
    -0.49
     PeEnEo
    -0.48
     rig
    -0.45
    tagHelperRunner
    -0.44
    rrggbb
    -0.43
     gan
    -0.43
     mention
    -0.41
     dimen
    -0.41
    XmlAccessorType
    -0.41
    POSITIVE LOGITS
    Internet
    0.68
     raiſ
    0.65
     Internet
    0.63
     zijne
    0.62
     uſed
    0.61
     ſtill
    0.60
     Majefty
    0.60
     becauſe
    0.59
     deſt
    0.58
     ſeveral
    0.57
    Activations Density 0.170%

    No Known Activations