© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 563
    Prev
    Next
    INDEX
    Explanations

    words related to different types of stone or marble

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

    Baroque Orchestra, nude dance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Flyers
    -0.52
    start
    -0.49
    set
    -0.47
     Confeder
    -0.47
    Start
    -0.46
    starts
    -0.46
    LOR
    -0.46
     LOR
    -0.46
     Autorisations
    -0.46
    Sig
    -0.45
    POSITIVE LOGITS
    Marble
    0.96
     Marble
    0.94
     marble
    0.93
    marble
    0.89
     mármol
    0.86
     márm
    0.65
     surla
    0.65
    GTCX
    0.60
     estatua
    0.59
     marbre
    0.58
    Activations Density 0.004%

    No Known Activations