© 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. 10-GEMMASCOPE-RES-16K
    6. 7799
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distance or limits in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sps
    -0.40
    opcao
    -0.40
    ene
    -0.40
    like
    -0.39
    搏
    -0.38
    bss
    -0.38
    شة
    -0.36
    ese
    -0.36
    -------
    -0.36
     Soni
    -0.36
    POSITIVE LOGITS
     far
    1.79
    Far
    1.62
     Far
    1.61
     FAR
    1.48
    far
    1.48
    FAR
    1.27
     daleko
    1.10
     farthest
    1.09
     jauh
    1.09
     farther
    1.05
    Activations Density 0.129%

    No Known Activations