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. 21-GEMMASCOPE-RES-16K
    6. 2279
    Prev
    Next
    INDEX
    Explanations

    specific attributes and operations related to software installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.85
     purpoſe
    -1.81
     houſe
    -1.78
     Monfieur
    -1.76
     Houſe
    -1.75
     Majefty
    -1.75
     ſeveral
    -1.62
     Diſ
    -1.62
     Efq
    -1.60
     Reſ
    -1.58
    POSITIVE LOGITS
     ‘
    0.67
     “
    0.66
     
    0.61
     e
    0.59
     et
    0.58
     am
    0.57
     bu
    0.57
     «
    0.57
     "
    0.56
     '
    0.55
    Activations Density 0.010%

    No Known Activations