© 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. 9-GEMMASCOPE-RES-16K
    6. 2437
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and materials related to diamond and hydrogels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -1.09
     propOrder
    -1.06
    \{\\
    -0.99
    +#+#
    -0.96
    AsUp
    -0.95
    
    -0.95
    IUrlHelper
    -0.93
     Braid
    -0.93
     Chit
    -0.93
    ########.
    -0.90
    POSITIVE LOGITS
     "
    0.73
    </b>
    0.62
    </td>
    0.62
     Diamond
    0.61
    </i>
    0.60
     htt
    0.60
     Slade
    0.59
     Alca
    0.56
     Schweitzer
    0.56
     cire
    0.55
    Activations Density 1.486%

    No Known Activations