© 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. 2-GEMMASCOPE-RES-16K
    11. 1386
    Prev
    Next
    INDEX
    Explanations

    interrogative and affirmative sentences, particularly in the context of questioning and answering

    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
     pinulongan
    -0.67
     esternos
    -0.64
     syn
    -0.61
    restes
    -0.59
    NEU
    -0.59
     OFDb
    -0.59
    ikon
    -0.57
    ecy
    -0.57
    arus
    -0.57
     חיצוניים
    -0.56
    POSITIVE LOGITS
    seamnă
    0.62
     GenerationType
    0.61
    GOTREF
    0.59
    Demografie
    0.58
     frumos
    0.57
     femininas
    0.57
     passim
    0.56
    UnusedPrivate
    0.56
     elettrico
    0.55
     estratég
    0.54
    Activations Density 0.433%

    No Known Activations