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. 8530
    Prev
    Next
    INDEX
    Explanations

    entities related to names and locations

    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
     purpoſe
    -1.19
     pleaſure
    -1.18
     houſe
    -1.18
     Majefty
    -1.11
     ſtate
    -1.01
     Reſ
    -1.01
     Monfieur
    -0.98
     Jefus
    -0.98
     Efq
    -0.97
     ſmall
    -0.97
    POSITIVE LOGITS
     nh
    0.66
     Th
    0.65
     thu
    0.62
     trong
    0.61
     tung
    0.61
     có
    0.60
     cho
    0.60
     ban
    0.59
     th
    0.58
     Quan
    0.58
    Activations Density 0.086%

    No Known Activations