© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8813
    Prev
    Next
    INDEX
    Explanations

    assertive statements regarding obligations or duties

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

    "It is"

    np_acts-logits-general · gemini-2.0-flash

    it is/would/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.69
    ChildScrollView
    -0.66
     ProtoMessage
    -0.65
    Chham
    -0.63
     صوتيه
    -0.62
    rungsseite
    -0.62
    URLException
    -0.62
    thâu
    -0.61
     ComVisible
    -0.60
    Personensuche
    -0.60
    POSITIVE LOGITS
    avadoc
    0.30
     mice
    0.30
     handelt
    0.26
    selectBy
    0.26
     Datei
    0.25
     hardly
    0.25
     happening
    0.25
    kaner
    0.24
     scarcely
    0.24
    imageFile
    0.24
    Activations Density 0.312%

    No Known Activations