© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    terms related to disabilities and related challenges faced by individuals

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

    disabilities or morality

    np_acts-logits-general · gemini-2.0-flash

    states of people

    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
    verwijspagina
    -0.56
    QMetaType
    -0.53
    сылкі
    -0.52
    LabelTagHelper
    -0.52
     requestCode
    -0.51
     CURLOPT
    -0.50
    ReusableCell
    -0.48
     للاسماء
    -0.47
    stylers
    -0.47
    tily
    -0.46
    POSITIVE LOGITS
     persons
    0.79
     people
    0.76
     individuals
    0.69
     person
    0.65
     personnes
    0.63
     patients
    0.55
     woman
    0.50
     ppl
    0.50
     clients
    0.50
     folks
    0.49
    Activations Density 0.804%

    No Known Activations