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. 15874
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific conditions or situations indicated by the word "under."

    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
     Pingback
    -0.76
    脚注の使い方
    -0.76
    RSpec
    -0.74
    })`
    -0.72
    bav
    -0.69
     Dav
    -0.69
     Carlin
    -0.69
     Zinn
    -0.68
    Portale
    -0.67
     LoginComponent
    -0.67
    POSITIVE LOGITS
    Under
    1.84
     Under
    1.82
     under
    1.81
    under
    1.72
    UNDER
    1.71
     UNDER
    1.68
    neath
    1.42
     Underwood
    1.33
    Bajo
    1.32
     sotto
    1.26
    Activations Density 0.149%

    No Known Activations