© 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. 5-GEMMASCOPE-RES-16K
    11. 15422
    Prev
    Next
    INDEX
    Explanations

    the presence of high activation or emphasis in sentences

    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
    хьтан
    -0.89
    CppMethod
    -0.83
     mergeFrom
    -0.81
    ]--;
    -0.78
    Datuak
    -0.78
     tartalomajánló
    -0.77
     سكانية
    -0.74
    __':
    -0.73
    __':
    -0.71
     BoxFit
    -0.68
    POSITIVE LOGITS
    eni
    0.49
     الحره
    0.48
     deberes
    0.48
     penuh
    0.46
     chủ
    0.45
    তি
    0.44
     nakalista
    0.44
    Биография
    0.44
    tere
    0.43
    uD
    0.43
    Activations Density 0.018%

    No Known Activations