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. 8-GEMMASCOPE-RES-16K
    6. 6067
    Prev
    Next
    INDEX
    Explanations

    references to opinions and introductory sections in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Архивная
    -0.75
    ட்ட
    -0.75
    

    -0.69
     Dha
    -0.68
     vals
    -0.68
     χα
    -0.66
    lys
    -0.66
    }^\
    -0.66
     Cess
    -0.66
    ovací
    -0.65
    POSITIVE LOGITS
    <u>
    1.31
    </u>
    1.02
     chré
    0.99
    ❤❤
    0.94
    underline
    0.93
     بيها
    0.88
     coraggio
    0.87
    SerializedSize
    0.85
    yscy
    0.83
     cadrul
    0.83
    Activations Density 0.125%

    No Known Activations