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. 2-GEMMASCOPE-RES-16K
    6. 6411
    Prev
    Next
    INDEX
    Explanations

    terms related to family and relationships, particularly in the context of obituaries or memorials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tény
    -0.47
     miliki
    -0.46
    estino
    -0.46
     Übergang
    -0.46
    ientí
    -0.45
    consejos
    -0.44
     Wikisource
    -0.44
    θεση
    -0.43
     Kowalski
    -0.43
    fh
    -0.43
    POSITIVE LOGITS
    éez
    0.70
    GEBURTSDATUM
    0.65
    adaptiveStyles
    0.65
    NameInMap
    0.65
    AndEndTag
    0.64
     onAnimation
    0.64
    RectangleBorder
    0.63
    IBarButtonItem
    0.62
    +#+#
    0.61
    AnchorStyles
    0.60
    Activations Density 0.057%

    No Known Activations