© 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. 38-GEMMASCOPE-RES-16K
    11. 8447
    Prev
    Next
    INDEX
    Explanations

    mentions of "Em" or similar variants related to a specific subject or identity context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IANGLES
    -0.48
    CPtr
    -0.48
    fjspx
    -0.42
    TestFixture
    -0.42
    XmlAccessType
    -0.41
     actualidad
    -0.41
     skolen
    -0.40
    gsmål
    -0.40
     متعلقه
    -0.40
     iVar
    -0.40
    POSITIVE LOGITS
     Em
    0.59
     em
    0.56
    Em
    0.50
     emb
    0.48
     EM
    0.46
     Emb
    0.45
    期刊论文
    0.42
    ERSON
    0.42
     ems
    0.41
     EMP
    0.40
    Activations Density 0.259%

    No Known Activations