© 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. 21-GEMMASCOPE-RES-16K
    11. 4769
    Prev
    Next
    INDEX
    Explanations

    instances of data manipulation and interactions involving variables and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.66
     doInBackground
    -0.60
    tagHelperRunner
    -0.58
    GEBURTSDATUM
    -0.56
    CloseOperation
    -0.56
     سكانية
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    RectangleBorder
    -0.53
    Enllaces
    -0.53
     विश्वसनीयता
    -0.53
    POSITIVE LOGITS
     twice
    2.58
    twice
    2.28
     thrice
    2.09
     multiple
    2.06
     Twice
    2.05
    Twice
    2.01
     once
    1.96
     TWICE
    1.88
     several
    1.88
    multiple
    1.84
    Activations Density 0.835%

    No Known Activations