© 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. 22-GEMMASCOPE-RES-16K
    11. 7682
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relational or comparative contexts among entities

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

    Phrases indicating composition or constitution

    np_acts-logits-general · gemini-2.0-flash

    `each`/`all`/`both` followed by `of` or participle verbs

    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
    ;
    -0.44
    ätta
    -0.41
    كذا
    -0.40
     quando
    -0.38
    When
    -0.37
    このような
    -0.37
    ish
    -0.36
    I
    -0.36
    ['
    -0.36
     -
    -0.36
    POSITIVE LOGITS
     requiring
    1.63
     consisting
    1.48
     featuring
    1.42
     resembling
    1.41
     involving
    1.37
     containing
    1.36
     needing
    1.36
     amounting
    1.36
     comprising
    1.33
     representing
    1.32
    Activations Density 0.535%

    No Known Activations