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. 23-GEMMASCOPE-RES-16K
    6. 5658
    Prev
    Next
    INDEX
    Explanations

    the word "come" and its variations in different forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    newswire
    -0.56
    PerformLayout
    -0.51
    LookAnd
    -0.49
    出版年
    -0.49
     szerint
    -0.47
     että
    -0.46
    ýš
    -0.46
    eadilan
    -0.45
     Suomessa
    -0.45
    MessageOf
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.69
     hand
    0.64
    ⓧ
    0.61
     packaged
    0.59
     complete
    0.58
    BeginContext
    0.58
     acompan
    0.57
     standard
    0.56
     paired
    0.56
     packed
    0.55
    Activations Density 0.096%

    No Known Activations