© 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. 21-GEMMASCOPE-RES-16K
    6. 16040
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and percentages related to populations or groups

    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
    autoreleasepool
    -0.45
     tyre
    -0.41
     Plätze
    -0.38
    miot
    -0.38
    tuig
    -0.38
     języka
    -0.37
     dziecka
    -0.37
    驹
    -0.37
    Izvori
    -0.37
     secas
    -0.37
    POSITIVE LOGITS
     فريبيس
    0.69
     CreateTagHelper
    0.58
    tagHelperRunner
    0.58
    featureID
    0.54
    AnchorStyles
    0.52
     pinulongan
    0.49
    TagMode
    0.48
     ProtoMessage
    0.47
    MessageOf
    0.47
    shadowOpacity
    0.46
    Activations Density 0.785%

    No Known Activations