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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12362
    Prev
    Next
    INDEX
    Explanations

    components related to knee prostheses and their materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    tvguidetime
    -0.56
     Genome
    -0.55
    posedge
    -0.54
     hígado
    -0.54
    #+#
    -0.53
    glLoadIdentity
    -0.53
    FormTagHelper
    -0.52
    GetAxis
    -0.52
    stateProvider
    -0.51
    $_['
    -0.51
    POSITIVE LOGITS
     material
    2.22
     materials
    2.21
    material
    1.97
     Materials
    1.88
    materials
    1.87
    Material
    1.86
     Material
    1.86
    Materials
    1.85
     materiales
    1.79
     materiais
    1.72
    Activations Density 0.494%

    No Known Activations