© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exclusivity or uniqueness

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

    Following the word "only."

    np_acts-logits-general · gemini-2.0-flash

    usage of "only"

    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
     lipat
    -0.52
     الحره
    -0.44
     poussière
    -0.40
     vaikka
    -0.37
    TemporalType
    -0.36
    setupUi
    -0.36
    iniums
    -0.35
    BibitemShut
    -0.34
    脚注の使い方
    -0.34
     mycket
    -0.34
    POSITIVE LOGITS
     remaining
    0.79
     thing
    0.78
    remaining
    0.65
     exception
    0.60
    Remaining
    0.59
    satunya
    0.59
     possible
    0.56
     truly
    0.56
     Remaining
    0.55
     reason
    0.55
    Activations Density 0.215%

    No Known Activations