Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1785
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to speed and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,$_
    -0.77
    Allo
    -0.74
     universitario
    -0.72
     institución
    -0.72
     Haram
    -0.70
     Rami
    -0.70
     ICM
    -0.69
    [@"
    -0.69
     forsaken
    -0.69
     zahrani
    -0.68
    POSITIVE LOGITS
     SPEED
    1.47
    SPEED
    1.45
     Speed
    1.40
    Speed
    1.35
     speed
    1.27
     speeds
    1.25
    speed
    1.24
    peed
    1.15
     Speeds
    1.15
    ocidad
    1.04
    Activations Density 0.041%

    No Known Activations