© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14967
    Prev
    Next
    INDEX
    Explanations

    formatted text elements, especially bolded and italicized sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.85
     pinulongan
    -0.75
    setViewportView
    -0.71
    DockStyle
    -0.68
    tonode
    -0.67
     ArrayAdapter
    -0.67
    GOTREF
    -0.67
     noDo
    -0.66
    AddTagHelper
    -0.66
    protoimpl
    -0.66
    POSITIVE LOGITS
    <strong>
    1.58
    <b>
    1.51
    <em>
    1.17
    <i>
    1.07
    <u>
    0.97
    <code>
    0.94
    <h1>
    0.69
    <sub>
    0.68
    <s>
    0.67
    mathbf
    0.60
    Activations Density 0.026%

    No Known Activations