© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10074
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Str" or variations of it, likely related to a specific programming or data structure context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EnglishChoose
    -0.62
     ویکی‌پدیای
    -0.61
    Архівовано
    -0.59
    <>());
    -0.58
    BaseEntity
    -0.57
     مشين
    -0.56
    yesi
    -0.55
    Hauptartikel
    -0.54
     convertView
    -0.54
    ESTIC
    -0.54
    POSITIVE LOGITS
     str
    1.80
     Str
    1.79
    str
    1.60
    Str
    1.59
     STR
    1.45
    STR
    1.30
     strata
    1.22
    strand
    1.16
     stra
    1.09
     strand
    1.08
    Activations Density 0.050%

    No Known Activations