© 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. 11072
    Prev
    Next
    INDEX
    Explanations

    connections or relationships in scientific or technical contexts

    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
     S
    -1.03
     J
    -0.98
     T
    -0.94
    o
    -0.93
     N
    -0.92
    S
    -0.92
     K
    -0.91
     D
    -0.90
     P
    -0.89
    E
    -0.89
    POSITIVE LOGITS
     themſelves
    1.63
     myſelf
    1.58
     itſelf
    1.55
     pleaſure
    1.48
    ſelves
    1.46
     ་་
    1.46
     Theſe
    1.44
     Monfieur
    1.44
     Efq
    1.41
     ―――――
    1.41
    Activations Density 1.024%

    No Known Activations