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

    Neuronpedia

    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. 5041
    Prev
    Next
    INDEX
    Explanations

    key actions or events, particularly those involving interactions and outcomes

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

    Followed by the word "one."

    np_acts-logits-general · gemini-2.0-flash

    the word one

    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
    RegressionTest
    -0.64
    __':
    -0.54
    tagHelperRunner
    -0.51
    featureID
    -0.50
    __":
    -0.50
     defStyleAttr
    -0.48
    exitRule
    -0.48
     invokingState
    -0.48
    __*/
    -0.47
     >=",
    -0.47
    POSITIVE LOGITS
     one
    1.45
    一个是
    1.20
     één
    1.05
     یکی
    0.91
     один
    0.90
     하나
    0.89
     одного
    0.89
    一つ
    0.89
     одну
    0.87
     jednego
    0.87
    Activations Density 0.457%

    No Known Activations