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. 22-GEMMASCOPE-RES-16K
    6. 10984
    Prev
    Next
    INDEX
    Explanations

    concepts related to health care management and organizational culture

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

    "that" or "which" as relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    emphasized harmony and acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ็จ
    -0.65
    ReactDOM
    -0.59
    classnames
    -0.58
     Besøkt
    -0.58
    BuildContext
    -0.57
    OpenHelper
    -0.57
     actualité
    -0.57
    hankelijk
    -0.56
    DidChange
    -0.56
    ButterKnife
    -0.54
    POSITIVE LOGITS
     emphasize
    1.24
     emphasis
    1.22
     emphasizes
    1.21
     prioriti
    1.19
     emphas
    1.17
     prioritize
    1.16
    emphas
    1.15
     Emphas
    1.13
     emphasise
    1.11
     emphasizing
    1.10
    Activations Density 0.532%

    No Known Activations