© 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. 20-GEMMASCOPE-RES-16K
    11. 11401
    Prev
    Next
    INDEX
    Explanations

    references to hidden actions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    område
    -0.45
    JsonFormat
    -0.42
     trường
    -0.39
     păr
    -0.38
     rate
    -0.38
    المكان
    -0.38
     språk
    -0.38
     Prayer
    -0.37
     prayer
    -0.37
    餐
    -0.37
    POSITIVE LOGITS
     BEHIND
    1.32
    Behind
    1.27
     Behind
    1.27
    behind
    1.24
     behind
    1.19
    Hinter
    0.92
     derrière
    0.87
     bakom
    0.83
     detrás
    0.81
     Hinter
    0.78
    Activations Density 0.043%

    No Known Activations