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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8507
    Prev
    Next
    INDEX
    Explanations

    instances of advice or requests related to family interactions

    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
    ագրություններ
    -0.48
    matchCondition
    -0.39
     referirse
    -0.38
     industrielle
    -0.35
    tetur
    -0.33
     człowieka
    -0.33
     Tôi
    -0.32
     czo
    -0.32
    teryx
    -0.32
    ########.
    -0.32
    POSITIVE LOGITS
     mom
    2.38
     Mom
    2.34
     Dad
    2.33
     dad
    2.23
    Mom
    2.23
    Dad
    2.17
     mum
    2.05
     Mum
    2.03
     mommy
    1.96
     Mommy
    1.93
    Activations Density 0.530%

    No Known Activations