© 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. 11-GEMMASCOPE-RES-16K
    6. 9901
    Prev
    Next
    INDEX
    Explanations

    references to "others" and their involvement or actions 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fhort
    -0.49
     idolat
    -0.47
    ihnachts
    -0.47
     AssemblyTitle
    -0.47
    ंदीखरीदारी
    -0.45
     Encyclo
    -0.45
    dirond
    -0.45
    変な
    -0.43
    MessageTagHelper
    -0.43
     føl
    -0.43
    POSITIVE LOGITS
    others
    1.02
    Others
    1.02
     others
    1.02
     Others
    1.01
     OTHERS
    0.91
    OTHERS
    0.69
     ours
    0.63
     Ours
    0.61
     دیگران
    0.60
    Ours
    0.59
    Activations Density 0.125%

    No Known Activations