© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11098
    Prev
    Next
    INDEX
    Explanations

    references to generalized concepts or frameworks in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    appearing before prepositions

    np_acts-logits-general · gemini-2.0-flash

    various / different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.54
     Wicidata
    -0.52
    ьаж
    -0.49
    OGND
    -0.49
    出版年
    -0.47
     Biôgrafia
    -0.47
    UnknownFieldSet
    -0.47
     autorytatywna
    -0.47
    EndProject
    -0.46
    verifyException
    -0.45
    POSITIVE LOGITS
     różnych
    0.60
     různ
    0.58
     variously
    0.58
     różne
    0.57
     disparate
    0.57
     olika
    0.56
     diferite
    0.56
     various
    0.55
     verschillende
    0.54
     verschiedenen
    0.54
    Activations Density 0.815%

    No Known Activations