© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12825
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mRecyclerView
    -0.39
     unloading
    -0.38
     Upload
    -0.38
     Upper
    -0.38
     SizedBox
    -0.38
     Gemeins
    -0.37
     Tare
    -0.36
     proven
    -0.36
     Asc
    -0.36
    loten
    -0.36
    POSITIVE LOGITS
    up
    2.05
    UP
    1.12
    upat
    0.82
    Up
    0.75
    upi
    0.73
    ups
    0.70
    uplo
    0.69
    upt
    0.68
    away
    0.68
    down
    0.68
    Activations Density 0.286%

    No Known Activations