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

    Neuronpedia

    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. 2-GEMMASCOPE-RES-16K
    11. 8838
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or degrees of quality

    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
    IntoConstraints
    -0.98
    Personendaten
    -0.84
     ModelExpression
    -0.83
     MainAxisSize
    -0.81
    UnusedPrivate
    -0.79
     CascadeType
    -0.74
    providedIn
    -0.71
    unknownFields
    -0.70
     IndexPath
    -0.69
    queous
    -0.68
    POSITIVE LOGITS
    单纯
    0.53
     benefit
    0.53
     better
    0.49
     côtés
    0.48
    かと
    0.48
    Autoritní
    0.48
    倾向
    0.48
    klere
    0.45
    cektir
    0.45
    YPE
    0.44
    Activations Density 0.245%

    No Known Activations