© 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. 18-GEMMASCOPE-RES-16K
    11. 2547
    Prev
    Next
    INDEX
    Explanations

    different versions of a specific software or document

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

    "version" followed by a number or punctuation

    np_acts-logits-general · gemini-2.0-flash

    version numbers and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delaire
    -0.61
    IntoConstraints
    -0.59
    çalves
    -0.56
     InputDecoration
    -0.54
     Japão
    -0.52
    onymes
    -0.50
    DEFINE
    -0.49
    utnik
    -0.46
    shiro
    -0.46
     חיצוניים
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.97
     getVersion
    0.90
     VERSION
    0.85
     Version
    0.82
     Versions
    0.81
     versions
    0.76
    getVersion
    0.75
     VERS
    0.74
     Vers
    0.71
    VERS
    0.70
    Activations Density 0.195%

    No Known Activations