© 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. 0-GEMMASCOPE-RES-16K
    6. 8947
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment

    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
     nghiệp
    -0.39
    Registry
    -0.37
    انجليز
    -0.37
    enschappelijke
    -0.36
    is
    -0.36
     độ
    -0.36
     object
    -0.35
    isand
    -0.35
    object
    -0.35
    memberof
    -0.35
    POSITIVE LOGITS
     thank
    2.81
     thanks
    2.64
    thanks
    2.50
    thank
    2.50
     Thank
    2.50
     THANKS
    2.48
     THANK
    2.42
     Thanks
    2.42
     thankful
    2.39
     thanking
    2.36
    Activations Density 0.174%

    No Known Activations