© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the comparative or superlative form along with contextual references

    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
    esModule
    -0.80
    #
    -0.78
     MonoBehaviour
    -0.76
    ynchronously
    -0.74
     Wicidata
    -0.67
    etcode
    -0.66
    PreferredItem
    -0.66
    CWE
    -0.65
    ++]=
    -0.63
    ngthen
    -0.63
    POSITIVE LOGITS
     than
    1.35
    than
    0.86
     THAN
    0.85
     niż
    0.82
    THAN
    0.82
    Than
    0.77
     hơn
    0.73
     Than
    0.69
     než
    0.68
     truer
    0.67
    Activations Density 0.255%

    No Known Activations