© 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. 38-GEMMASCOPE-RES-16K
    11. 9000
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high emphasis on quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一部
    -0.43
    
    -0.42
    ★★★★☆
    -0.38
     kasarigan
    -0.37
    Occasionally
    -0.36
    essentiel
    -0.36
    🔕
    -0.35
    )_/¯
    -0.35
    исленность
    -0.35
     الرياضيه
    -0.35
    POSITIVE LOGITS
     many
    3.28
    many
    2.64
    Many
    2.42
     Many
    2.39
     MANY
    2.22
     många
    2.13
     muchos
    2.11
     vielen
    2.11
     viele
    2.08
    MANY
    2.06
    Activations Density 0.686%

    No Known Activations