© 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. 5701
    Prev
    Next
    INDEX
    Explanations

    patterns of citations or references within legal documents

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

    Numbers followed by various mathematical notations

    np_acts-logits-general · gemini-2.0-flash

    mathematical sequences

    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
     صوتيه
    -0.67
     leſs
    -0.64
     المعيارى
    -0.63
     مرئيه
    -0.63
     '\\;'
    -0.61
     ſmall
    -0.61
    neſs
    -0.59
     ſtate
    -0.58
     incomplète
    -0.58
     ſy
    -0.58
    POSITIVE LOGITS
    complexType
    0.58
    UnknownFieldSet
    0.52
    featureID
    0.51
    bitField
    0.49
     Lightboxes
    0.48
    örgy
    0.48
    AddTagHelper
    0.46
    ↻
    0.46
    htbp
    0.45
     lucru
    0.45
    Activations Density 0.777%

    No Known Activations