© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10418
    Prev
    Next
    INDEX
    Explanations

    issues related to digital communication and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Negative or null statements

    np_acts-logits-general · gemini-2.0-flash

    sentences without conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nicht
    -0.45
    不该
    -0.38
    χι
    -0.37
     shouldnt
    -0.37
    却没有
    -0.36
     niet
    -0.36
    不宜
    -0.36
     não
    -0.35
     isnt
    -0.34
     aldrig
    -0.34
    POSITIVE LOGITS
     nor
    1.02
    nor
    0.84
     Nor
    0.84
    Nor
    0.82
     Tampoco
    0.78
     melainkan
    0.74
     anzi
    0.71
     only
    0.71
     nemmeno
    0.71
    也沒有
    0.69
    Activations Density 0.761%

    No Known Activations