© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14937
    Prev
    Next
    INDEX
    Explanations

    elements related to structure and organization of information

    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
     صوتيه
    -0.62
    GOTREF
    -0.62
    tvguidetime
    -0.60
    MENAFN
    -0.58
    CGRectMake
    -0.56
     GenerationType
    -0.53
     насељу
    -0.53
    sizeCache
    -0.52
    RSpec
    -0.51
    nestjs
    -0.49
    POSITIVE LOGITS
     concluding
    2.38
     ending
    2.28
     conclusion
    2.17
     conclude
    2.13
     concludes
    2.09
     finale
    2.09
     finishing
    2.05
     closing
    2.04
     concluded
    2.00
     Concluding
    1.98
    Activations Density 0.432%

    No Known Activations