© 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. 7-GEMMASCOPE-RES-16K
    11. 1898
    Prev
    Next
    INDEX
    Explanations

    instances where the word "just" and variations of "as" are used in conjunction with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     denn
    -0.64
    jspx
    -0.60
    XMLSchema
    -0.58
     more
    -0.57
    DECL
    -0.56
    <()>
    -0.53
    atel
    -0.53
     Einwilligung
    -0.52
    šanai
    -0.52
    ياة
    -0.51
    POSITIVE LOGITS
     Roskov
    0.69
     للمعارف
    0.67
     Propriété
    0.66
     '\\;'
    0.65
     newBuilder
    0.64
    didSet
    0.64
    ApiModel
    0.63
    kurat
    0.63
     cikin
    0.63
     مباشرة
    0.62
    Activations Density 0.160%

    No Known Activations