© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9877
    Prev
    Next
    INDEX
    Explanations

    phrases related to obtaining or achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     itſelf
    -1.21
     purpoſe
    -1.09
     ſtate
    -1.01
     Trix
    -1.00
     reaſon
    -0.98
    setVerticalGroup
    -0.93
     themſelves
    -0.90
     Ballo
    -0.90
     neceff
    -0.90
    awtextra
    -0.90
    POSITIVE LOGITS
     get
    1.65
     gets
    1.55
     got
    1.49
     getting
    1.49
    Gets
    1.48
     Get
    1.37
     gotten
    1.37
     GETS
    1.34
    Getting
    1.33
    get
    1.33
    Activations Density 0.092%

    No Known Activations