© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13455
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational processes and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.68
    tagHelperRunner
    -0.63
    enumi
    -0.59
    httphttps
    -0.50
     ligiloj
    -0.50
    Spolja
    -0.48
    KommentareTeilen
    -0.47
     surla
    -0.47
    ackerel
    -0.46
    OGND
    -0.46
    POSITIVE LOGITS
    </h2>
    0.57
    </b>
    0.57
    </strong>
    0.54
    </h3>
    0.54
     betweenstory
    0.43
    AndroidJUnit
    0.43
    </h1>
    0.42
    CodedInputStream
    0.42
    </h4>
    0.39
     resourceCulture
    0.39
    Activations Density 0.702%

    No Known Activations