© 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. 16171
    Prev
    Next
    INDEX
    Explanations

    expressions of self-identification and emotional states

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

    "is" or "am" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be"

    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
    mousse
    -0.65
     Italijani
    -0.65
     podjela
    -0.65
    ParseTree
    -0.64
    ніципалі
    -0.63
    ItemBackground
    -0.60
     المعيارى
    -0.58
    +#+#
    -0.58
    EDEFAULT
    -0.57
    Aussie
    -0.57
    POSITIVE LOGITS
    mektedir
    0.68
    maktadır
    0.58
    melidir
    0.57
    cektir
    0.47
     yoktur
    0.47
     جدًا
    0.46
     skall
    0.46
     sahiptir
    0.45
    ियाँ
    0.44
     upon
    0.44
    Activations Density 0.579%

    No Known Activations