© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2111
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" in various contexts

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

    `this` member access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erreferentziak
    -0.49
     intensifies
    -0.41
    isan
    -0.41
     Ozark
    -0.40
     Beren
    -0.40
     testSet
    -0.40
     Andean
    -0.40
     rainforest
    -0.38
     PGC
    -0.38
     Aran
    -0.38
    POSITIVE LOGITS
     مُعرِّف
    0.67
    glLoadIdentity
    0.64
    żd
    0.64
     onAnimation
    0.64
    sizeCache
    0.63
    uxxxx
    0.63
    허
    0.63
    SBATCH
    0.63
     StringField
    0.62
    rophore
    0.62
    Activations Density 0.021%

    No Known Activations