© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3130
    Prev
    Next
    INDEX
    Explanations

    References to various types of locations and contexts, particularly related to camps, legal terms, and customer service situations

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

    Word is followed by relatively uncommon words

    np_acts-logits-general · gemini-2.0-flash

    hall, camp, space, day, counsel, customs

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Viungo
    -0.51
    yntaxException
    -0.50
    ConstraintMaker
    -0.49
    HideFlags
    -0.49
    colgante
    -0.49
    쩔
    -0.47
    ArrowToggle
    -0.47
    AddTagHelper
    -0.47
     vindo
    -0.46
     TAMBÉM
    -0.46
    POSITIVE LOGITS
    Geplaatst
    0.47
    NameInMap
    0.45
    catraz
    0.39
    ً
    0.38
    detectChanges
    0.36
    opardy
    0.36
     Qaeda
    0.36
    MeasureSpec
    0.35
    testing
    0.35
     intptr
    0.34
    Activations Density 1.135%

    No Known Activations