© 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. 24-GEMMASCOPE-RES-16K
    11. 1801
    Prev
    Next
    INDEX
    Explanations

    phrases related to character attributes and actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows forms of "be" ("is", "was", "were")

    np_acts-logits-general · gemini-2.0-flash

    enlarged before destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecap
    -0.43
     SwitchCompat
    -0.41
    ipal
    -0.41
    sst
    -0.41
    antic
    -0.40
     Vita
    -0.40
    SLP
    -0.40
    хьтан
    -0.40
    iales
    -0.40
    tone
    -0.39
    POSITIVE LOGITS
    queryInterface
    0.74
    SharedDtor
    0.63
    OCCURRED
    0.60
     Signalez
    0.58
    Tē
    0.57
    WillAppear
    0.55
    ViewImports
    0.54
     
    0.54
    msgTypes
    0.54
     pinulongan
    0.53
    Activations Density 1.393%

    No Known Activations