Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15246
    Prev
    Next
    INDEX
    Explanations

    references to personal belongings or possessions

    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
     himself
    -0.97
     Himself
    -0.80
    himself
    -0.79
     koji
    -0.78
     који
    -0.68
     Jr
    -0.65
     Filho
    -0.63
    くん
    -0.61
     الدولى
    -0.58
    ionado
    -0.58
    POSITIVE LOGITS
     herself
    1.60
    herself
    1.13
     bint
    0.92
     she
    0.88
     powinna
    0.80
     shes
    0.79
     lesbian
    0.77
     actress
    0.76
    حياتها
    0.76
     her
    0.76
    Activations Density 1.737%

    No Known Activations