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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to the ages of children and their descriptions

    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-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
    __(/*!
    -0.57
    TagHelper
    -0.47
     CreateTagHelper
    -0.47
    ">//
    -0.45
    发表于
    -0.42
    getSystemService
    -0.40
    BufferException
    -0.39
     Handeln
    -0.39
    íncia
    -0.38
     насељу
    -0.37
    POSITIVE LOGITS
     preschool
    0.69
     toddlers
    0.65
     kindergarten
    0.64
     preescolar
    0.64
     Preschool
    0.60
     toddler
    0.60
     Toddler
    0.58
    小学
    0.58
    Kindergarten
    0.57
     Kindergarten
    0.56
    Activations Density 0.149%

    No Known Activations