Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8636
    Prev
    Next
    INDEX
    Explanations

    elements related to hospitality and cultural experiences

    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
    AndEndTag
    -0.84
     unknownFields
    -0.70
     AssemblyCompany
    -0.60
    parsedMessage
    -0.58
    UnusedPrivate
    -0.58
    featureID
    -0.57
    henswürdigkeiten
    -0.57
    昼食
    -0.56
    الدراسه
    -0.53
    rlpool
    -0.53
    POSITIVE LOGITS
     hipster
    0.84
     cowork
    0.67
     hip
    0.64
     artisanal
    0.64
     indie
    0.63
    hipster
    0.60
     spea
    0.60
     boho
    0.58
     vegan
    0.57
     pop
    0.57
    Activations Density 0.316%

    No Known Activations