© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9934
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to legal proceedings and allegations

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

    Followed by a verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    forms structure

    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
    ztály
    -0.62
    طيع
    -0.59
    +:+
    -0.57
    arxiv
    -0.56
    참고
    -0.56
    icina
    -0.55
    awtextra
    -0.54
    embre
    -0.54
    ędzynarod
    -0.54
    esModule
    -0.53
    POSITIVE LOGITS
     forms
    1.50
     form
    1.36
     forming
    1.26
    forms
    1.21
     Forming
    1.17
     FORMS
    1.15
     formed
    1.15
     Forms
    1.14
     formar
    1.09
    Forms
    1.08
    Activations Density 0.847%

    No Known Activations