© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 2659
    Prev
    Next
    INDEX
    Explanations

    some form of decision-making or transitions in life events

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

    choices and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colorado
    -0.37
    %)$
    -0.36
    stag
    -0.36
     DIN
    -0.35
    MACH
    -0.34
     Cm
    -0.34
     Mg
    -0.34
    ⇑
    -0.34
    المناصب
    -0.34
     cm
    -0.34
    POSITIVE LOGITS
     instead
    0.57
     AssemblyCulture
    0.57
    instead
    0.57
    IntoConstraints
    0.56
     finalement
    0.56
    Espèce
    0.50
    Instead
    0.49
     letzt
    0.49
     zamiast
    0.49
    SuppressLint
    0.48
    Activations Density 0.063%

    No Known Activations