Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51878
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to method definitions and string representations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     pinulongan
    -0.76
    GEBURTS
    -0.74
     CreateTagHelper
    -0.73
     الحره
    -0.71
    :✨
    -0.65
    IsContent
    -0.64
     يتيمه
    -0.64
    تقاوى
    -0.63
    ########.
    -0.61
    StoryboardSegue
    -0.60
    POSITIVE LOGITS
    cemment
    0.42
     święta
    0.41
     său
    0.40
     Sünden
    0.40
     policial
    0.39
     marbre
    0.38
     vôtre
    0.38
     avoient
    0.38
     declaração
    0.36
     armées
    0.35
    Activations Density 0.001%

    No Known Activations