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. 12-GEMMASCOPE-RES-16K
    6. 14856
    Prev
    Next
    INDEX
    Explanations

    terms related to familial relationships, particularly involving grandparents and grandchildren

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.72
    )__
    -0.59
    ovski
    -0.59
    antía
    -0.59
    [--
    -0.59
    âche
    -0.57
    PANY
    -0.57
    oves
    -0.57
    aky
    -0.56
    osoba
    -0.55
    POSITIVE LOGITS
     grandchildren
    0.81
    grandchildren
    0.77
     grandchild
    0.75
     grandkids
    0.65
     grandsons
    0.61
     granddaughter
    0.58
    middels
    0.57
     grandson
    0.55
     jadx
    0.52
     kaynağından
    0.51
    Activations Density 0.037%

    No Known Activations