© 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. 28-GEMMASCOPE-RES-16K
    6. 7250
    Prev
    Next
    INDEX
    Explanations

    descriptors of scenes portraying conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispensation
    -0.34
    things
    -0.27
     THING
    -0.27
     venture
    -0.26
     altra
    -0.25
    tvguidetime
    -0.25
     matters
    -0.25
     THINGS
    -0.25
     decision
    -0.24
     Things
    -0.24
    POSITIVE LOGITS
    ValueStyle
    0.71
    NameInMap
    0.68
    featureID
    0.68
    complexContent
    0.66
     ModelExpression
    0.65
     autorytatywna
    0.63
    bootstrapcdn
    0.62
    Autoritní
    0.60
     архивлан
    0.60
     Chwiliwch
    0.60
    Activations Density 0.051%

    No Known Activations