© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15735
    Prev
    Next
    INDEX
    Explanations

    numeric data representing choices or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -1.03
     pleaſure
    -0.93
     EconPapers
    -0.93
     navideña
    -0.88
     GenerationType
    -0.88
     defaultstate
    -0.87
    دانشنامهٔ
    -0.86
     otomatig
    -0.85
    fjspx
    -0.82
     ſtate
    -0.82
    POSITIVE LOGITS
    '
    0.71
    ​
    0.67
     man
    0.54
    )
    0.52
     Ce
    0.50
    s
    0.50
    ’
    0.50
     ce
    0.48
    \
    0.48
    </em>
    0.47
    Activations Density 0.182%

    No Known Activations