© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2454
    Prev
    Next
    INDEX
    Explanations

    references to "similar" in various contexts

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

    Words/phrases indicating similarity

    np_acts-logits-general · gemini-2.0-flash

    similar followed by another word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    stateProvider
    -0.57
     المعيارى
    -0.55
    charCode
    -0.52
    returnValue
    -0.51
     penna
    -0.48
    fbox
    -0.48
    formData
    -0.46
    olisme
    -0.45
     NavController
    -0.44
    gypti
    -0.43
    POSITIVE LOGITS
    Similar
    1.25
     similar
    1.23
     Similar
    1.22
    similar
    1.20
     SIMILAR
    1.10
     similaire
    1.03
     ähnliche
    0.98
     ähnlichen
    0.90
     ähn
    0.87
     similares
    0.84
    Activations Density 0.182%

    No Known Activations