© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2841
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to calibration and measurement processes

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

    ending in "ating", "izing", "ting" or "lying"

    np_acts-logits-general · gemini-2.0-flash

    verbs ending in -ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    rungsseite
    -0.68
    ishment
    -0.66
    GEBURTSDATUM
    -0.63
    lihood
    -0.63
     miniaturka
    -0.62
    WriteAttribute
    -0.59
    mmation
    -0.57
    membrance
    -0.57
     Ouverture
    -0.57
    nement
    -0.57
    POSITIVE LOGITS
     inspecting
    0.38
    ulating
    0.37
    vating
    0.37
     assaulting
    0.37
    tifying
    0.37
     defending
    0.36
    ngiliz
    0.36
    ''')
    0.36
     translating
    0.36
     collaborating
    0.36
    Activations Density 1.627%

    No Known Activations