© 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. 2-GEMMASCOPE-RES-16K
    6. 8310
    Prev
    Next
    INDEX
    Explanations

    sentiments related to fan engagement and criticism in media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eben
    -0.53
    üyor
    -0.53
    istik
    -0.52
     INCLUD
    -0.51
    oides
    -0.51
    worten
    -0.51
    itious
    -0.50
     متعلقه
    -0.50
    Versions
    -0.50
    hofer
    -0.49
    POSITIVE LOGITS
     Wikispecies
    0.69
    XMLSchema
    0.64
    syms
    0.61
     typelib
    0.57
     للمعارف
    0.56
     ویکی‌پدیا
    0.56
     informée
    0.55
    asyarakat
    0.55
    IVEREF
    0.54
     createState
    0.54
    Activations Density 0.351%

    No Known Activations