© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6571
    Prev
    Next
    INDEX
    Explanations

    phrases or events related to abandonment or loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.56
     createState
    -0.40
    참고
    -0.38
    ViewImports
    -0.37
    ----</
    -0.36
    Witam
    -0.35
    MarshalTo
    -0.34
    addCriterion
    -0.33
     télévis
    -0.33
     negru
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.49
    ptonshire
    0.46
    الحياه
    0.45
     jspb
    0.44
    findpost
    0.42
     señ
    0.42
     defence
    0.42
    nerable
    0.42
     defenses
    0.41
     traced
    0.41
    Activations Density 0.391%

    No Known Activations