© 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. 4-GEMMASCOPE-RES-16K
    11. 9926
    Prev
    Next
    INDEX
    Explanations

    instances of arbitrary content or elements within complex structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.69
     
    -0.68
     A
    -0.63
      
    -0.58
    a
    -0.56
    .
    -0.55
     \
    -0.52
    -
    -0.52
    ↵
    -0.51
    1
    -0.51
    POSITIVE LOGITS
     myſelf
    1.26
     Houſe
    1.19
     purpoſe
    1.13
     houſe
    1.10
     itſelf
    1.09
     Reſ
    1.08
     Eſ
    1.07
    ništ
    1.05
     Efq
    1.05
    ſelf
    1.04
    Activations Density 0.028%

    No Known Activations