© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9743
    Prev
    Next
    INDEX
    Explanations

    words related to exploring or uncovering information

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

    "dig" or "digital"

    np_acts-logits-general · gemini-2.0-flash

    digging and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orm
    -0.45
     Bench
    -0.43
     штат
    -0.40
     noten
    -0.40
     Jans
    -0.39
     שוליים
    -0.39
    Orm
    -0.37
     Ist
    -0.36
     Arn
    -0.36
    ếu
    -0.36
    POSITIVE LOGITS
     Dig
    0.98
    Dig
    0.98
     dig
    0.96
     DIG
    0.79
     digging
    0.79
     digger
    0.77
     Digi
    0.75
    DIG
    0.73
     dug
    0.73
     digs
    0.72
    Activations Density 0.088%

    No Known Activations