© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7317
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to inventions, innovations, and technological processes

    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
    Elő
    -0.33
    moins
    -0.33
     Less
    -0.32
    ㍑
    -0.31
    cemia
    -0.31
     moins
    -0.31
    omio
    -0.31
     repente
    -0.30
     predecessor
    -0.30
    adeloupe
    -0.30
    POSITIVE LOGITS
     further
    4.22
    further
    3.75
    Further
    3.42
     Further
    3.34
     FURTHER
    3.25
    FURTHER
    2.72
    进一步
    2.42
    urther
    2.36
     weiter
    2.33
     farther
    2.25
    Activations Density 1.413%

    No Known Activations