© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6621
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to transferring and transforming information or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Trans" or "transfer" and related words

    np_acts-logits-general · gemini-2.0-flash

    transfer and trans variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paravant
    -0.60
    wertig
    -0.54
     bookId
    -0.51
    getScore
    -0.51
     fédé
    -0.49
     Houſe
    -0.48
    œil
    -0.46
    kijken
    -0.46
     quiser
    -0.46
     roomId
    -0.46
    POSITIVE LOGITS
     transfer
    0.95
     trans
    0.91
     Trans
    0.86
     Transfer
    0.81
     transport
    0.80
     transfers
    0.79
     transf
    0.77
     MonoBehaviour
    0.77
    transfer
    0.77
     transition
    0.73
    Activations Density 0.219%

    No Known Activations