© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9602
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal permissions and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dė
    -0.57
    HostException
    -0.56
     gerichtet
    -0.50
     GetEnumerator
    -0.49
     localObject
    -0.48
    тельству
    -0.48
     Entfernung
    -0.47
    feldt
    -0.46
    tır
    -0.45
    Incomplete
    -0.45
    POSITIVE LOGITS
     protoimpl
    0.90
     tolerance
    0.84
     flexibility
    0.82
    bootstrapcdn
    0.76
     Tolerance
    0.75
    tolerance
    0.74
     Toler
    0.74
     forgiving
    0.74
    余裕
    0.73
    MessageTagHelper
    0.73
    Activations Density 0.304%

    No Known Activations