© 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. 8-GEMMASCOPE-RES-16K
    11. 4945
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the progression of a scientific analysis or study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.31
     Jefus
    -1.14
     Monfieur
    -1.05
    StoryboardSegue
    -1.03
     Theſe
    -1.03
     pleaſure
    -1.01
     faſt
    -0.99
     houſe
    -0.99
     Houſe
    -0.99
     beginnetje
    -0.98
    POSITIVE LOGITS
     also
    0.73
     specifically
    0.63
     همچنین
    0.59
     principalement
    0.58
     также
    0.58
     primarily
    0.58
     tratando
    0.55
    तः
    0.54
     följande
    0.52
     juos
    0.51
    Activations Density 0.674%

    No Known Activations