© 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. 2-GEMMASCOPE-RES-16K
    11. 4662
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the letter 't' and negations

    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
     Morm
    -0.83
     consecration
    -0.70
     Paglinawan
    -0.70
     Reihen
    -0.70
     délic
    -0.67
     BFS
    -0.67
     biologie
    -0.67
    Composable
    -0.66
     frescoes
    -0.65
     Circ
    -0.64
    POSITIVE LOGITS
     was
    1.10
     not
    1.09
     did
    0.97
     had
    0.90
     wasn
    0.89
     WAS
    0.88
     didn
    0.86
     could
    0.83
     Was
    0.82
     didnt
    0.80
    Activations Density 0.137%

    No Known Activations