© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15971
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal belongings and attachment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estadounid
    -0.57
     بگو
    -0.53
    はいけない
    -0.50
     éc
    -0.50
     Piac
    -0.50
     ſind
    -0.49
     ماذا
    -0.48
     ſi
    -0.47
    知っている
    -0.47
    ijk
    -0.46
    POSITIVE LOGITS
     gettin
    0.92
     lotta
    0.82
     outta
    0.81
     gonna
    0.79
     lookin
    0.79
    gonna
    0.77
     somethin
    0.77
     nothin
    0.76
     goin
    0.75
     sayin
    0.75
    Activations Density 0.451%

    No Known Activations