© 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. 14-GEMMASCOPE-RES-16K
    11. 2623
    Prev
    Next
    INDEX
    Explanations

    phrases relating to actions, particularly those involving plans, accomplishments, and collaborative efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -1.10
     houſe
    -1.10
     Chriftian
    -1.09
     purpoſe
    -1.08
     متعلقه
    -1.07
     ſtate
    -1.04
     fubject
    -1.03
     ISNI
    -1.02
    mybatisplus
    -1.01
     greateſt
    -1.01
    POSITIVE LOGITS
     also
    0.75
    :
    0.63
     
    0.59
     often
    0.56
     usually
    0.52
     have
    0.51
     a
    0.51
     much
    0.51
     no
    0.49
     even
    0.48
    Activations Density 0.444%

    No Known Activations