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. 15-GEMMASCOPE-RES-16K
    6. 1439
    Prev
    Next
    INDEX
    Explanations

    terms related to positioning and layout in CSS or HTML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.99
    GEBURTSDATUM
    -0.78
    shadowRadius
    -0.78
     henvisninger
    -0.78
     AppColors
    -0.76
    edicated
    -0.74
    ientí
    -0.73
    Tracce
    -0.73
    jetunion
    -0.73
     cherchés
    -0.72
    POSITIVE LOGITS
     position
    1.67
     positions
    1.59
     Position
    1.49
    Position
    1.41
     POSITION
    1.39
    position
    1.39
     Positions
    1.31
    Positions
    1.27
     getPosition
    1.14
    POSITION
    1.10
    Activations Density 0.128%

    No Known Activations