© 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. 0-GEMMASCOPE-RES-16K
    11. 9282
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types or settings of food and drink

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tumba
    -0.42
    Autoritní
    -0.40
     băr
    -0.40
     médaille
    -0.36
    empatan
    -0.35
     Batalla
    -0.34
     aikaa
    -0.34
     récompense
    -0.34
     óptica
    -0.34
     contemporánea
    -0.34
    POSITIVE LOGITS
     Fi
    2.06
     fi
    1.91
    Fi
    1.87
     fis
    1.83
    fi
    1.67
     фи
    1.67
     FI
    1.66
    fib
    1.66
    fis
    1.65
     Fis
    1.63
    Activations Density 1.235%

    No Known Activations