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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 15772
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     U
    -0.55
    chle
    -0.52
    zey
    -0.50
    plaatst
    -0.49
    romolecules
    -0.48
    führer
    -0.48
    drav
    -0.48
     кӀош
    -0.47
    bolista
    -0.47
    ichè
    -0.47
    POSITIVE LOGITS
     grandchildren
    1.32
     grandkids
    1.19
     daughters
    1.17
     grandsons
    1.04
     grandchild
    1.03
     children
    1.00
    grandchildren
    1.00
    children
    0.93
     daughter
    0.91
     hijos
    0.91
    Activations Density 0.111%

    No Known Activations