© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2172
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and scientific terminology, particularly in the context of fluids and substances

    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
     Monfieur
    -2.00
     myſelf
    -1.94
     Reſ
    -1.87
     itſelf
    -1.86
     Anſ
    -1.86
     Efq
    -1.83
     Diſ
    -1.83
     pleaſure
    -1.81
     purpoſe
    -1.80
     whoſe
    -1.78
    POSITIVE LOGITS
     de
    0.70
     la
    0.65
     et
    0.60
     „
    0.57
     o
    0.55
    ,
    0.54
     i
    0.51
    -
    0.51
     a
    0.48
     n
    0.47
    Activations Density 0.006%

    No Known Activations