© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15473
    Prev
    Next
    INDEX
    Explanations

    academic citations and references formatted in a specific style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.86
     Diſ
    -0.81
     Efq
    -0.80
     Perſ
    -0.79
     المعيارى
    -0.79
     Inſ
    -0.79
     ſeveral
    -0.78
     Theſe
    -0.76
    ]--;
    -0.74
     Monfieur
    -0.73
    POSITIVE LOGITS
    WebControls
    0.67
    afone
    0.48
    发表于
    0.47
    الإنجليزية
    0.44
     E
    0.44
    forName
    0.43
    <!--[
    0.43
    varing
    0.43
     na
    0.42
     so
    0.42
    Activations Density 0.186%

    No Known Activations