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. 12-GEMMASCOPE-RES-16K
    6. 2740
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic struggles and societal critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    GEBURTSDATUM
    -0.78
     CreateTagHelper
    -0.72
     utafitiHapana
    -0.66
     صوتيه
    -0.63
    存于互联网档案馆
    -0.62
     ExecuteAsync
    -0.60
    Архівовано
    -0.60
     estekak
    -0.60
     snippetHide
    -0.60
     propOrder
    -0.59
    POSITIVE LOGITS
     burgeoning
    0.46
     mundane
    0.45
    albeit
    0.45
     foray
    0.44
     intricacies
    0.44
     albeit
    0.43
     caveats
    0.43
    Fazit
    0.42
     spiaggia
    0.42
     daunting
    0.42
    Activations Density 3.595%

    No Known Activations