© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11205
    Prev
    Next
    INDEX
    Explanations

    references to tragic or impactful events

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

    after prepositions or near locations

    np_acts-logits-general · gemini-2.0-flash

    locations after prepositions

    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
     Flushing
    -0.60
    ioutil
    -0.55
    Adapters
    -0.52
     Waray
    -0.48
    diyesi
    -0.48
    Bron
    -0.48
    asi
    -0.46
     Fontana
    -0.46
    remont
    -0.46
    stdafx
    -0.46
    POSITIVE LOGITS
    Personensuche
    0.74
     ExecuteAsync
    0.72
    Manbalar
    0.72
     الحره
    0.70
    sizeCache
    0.62
     nahilalakip
    0.62
    ocino
    0.60
    /**
    0.59
    IsMutable
    0.57
    AndEndTag
    0.55
    Activations Density 0.133%

    No Known Activations