© 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. 21-GEMMASCOPE-RES-16K
    11. 2186
    Prev
    Next
    INDEX
    Explanations

    elements related to requests and procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.75
     surla
    -0.70
     Ανακτήθηκε
    -0.70
    findpost
    -0.67
     initComponents
    -0.67
    Eles
    -0.67
    Datuak
    -0.67
     Obrador
    -0.66
     Exactos
    -0.66
    تقاوى
    -0.66
    POSITIVE LOGITS
     the
    1.29
     those
    1.24
     what
    1.23
     some
    1.18
     את
    1.09
     a
    1.07
     an
    0.98
     any
    0.96
     something
    0.96
     những
    0.94
    Activations Density 0.474%

    No Known Activations