© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10076
    Prev
    Next
    INDEX
    Explanations

    references to family connections and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     collega
    -0.38
     mitra
    -0.38
     Aristi
    -0.37
     Host
    -0.37
     arg
    -0.36
    ClassName
    -0.35
     Hump
    -0.34
    groups
    -0.34
     plug
    -0.34
    penny
    -0.33
    POSITIVE LOGITS
     family
    1.43
     father
    1.37
     familial
    1.33
     familiale
    1.29
    family
    1.24
     siblings
    1.24
     sibling
    1.18
     FAMILY
    1.18
    Family
    1.13
    father
    1.10
    Activations Density 0.767%

    No Known Activations