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

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-16K
    11. 10096
    Prev
    Next
    INDEX
    Explanations

    terms related to penetration and diffusion processes

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

    The neuron detects words or phrases related to penetration or movement through a substance, barrier, or structure.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    责编
    -0.39
     ơi
    -0.38
    ohjel
    -0.38
     Fav
    -0.37
     emoc
    -0.36
    setLoading
    -0.36
    BibitemShut
    -0.36
     Obs
    -0.35
     perkara
    -0.35
    ndef
    -0.35
    POSITIVE LOGITS
     penetrate
    1.38
     penetrated
    1.36
     penetrating
    1.25
     penetration
    1.23
     penet
    1.20
     penetrates
    1.20
     Penetration
    1.13
     проник
    1.11
     infiltrated
    1.05
    penet
    1.04
    Activations Density 0.448%

    No Known Activations