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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8768
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical formation processes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.62
    Хьажоргаш
    -0.61
     AsyncTask
    -0.60
    adeloupe
    -0.58
     للمعارف
    -0.58
    WireFormatLite
    -0.57
    قایناق‌لار
    -0.56
     oxidase
    -0.56
     useCallback
    -0.56
    AndEndTag
    -0.55
    POSITIVE LOGITS
     formation
    1.19
     formed
    1.16
     Formation
    1.15
    Formation
    1.10
     forming
    1.10
     FORMATION
    1.04
     Forming
    0.97
     Formed
    0.97
     formations
    0.96
    formation
    0.94
    Activations Density 0.206%

    No Known Activations