© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 847
    Prev
    Next
    INDEX
    Explanations

    phrases that specify objectives, purposes, and significant provisions within a context

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

    "of which" or relating to relative clauses

    np_acts-logits-general · gemini-2.0-flash

    of which/whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.65
    Хьажоргаш
    -0.59
     Numerade
    -0.56
     Wikimedijinoj
    -0.55
    lapsingToolbar
    -0.53
     propOrder
    -0.53
    expandindo
    -0.49
    Apre
    -0.47
    rophobic
    -0.47
    isfile
    -0.47
    POSITIVE LOGITS
     which
    2.32
    which
    1.67
     WHICH
    1.62
     Which
    1.59
    Which
    1.52
     whom
    1.39
     whose
    1.29
     ambayo
    1.13
     laquelle
    1.13
     lequel
    1.11
    Activations Density 0.149%

    No Known Activations