© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4274
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of hops or jumping actions, often in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.72
     vectorielles
    -0.52
     capuz
    -0.50
     picioare
    -0.50
     élas
    -0.50
     brancas
    -0.50
     مشين
    -0.49
     Numerade
    -0.49
     étro
    -0.48
     vermelhas
    -0.48
    POSITIVE LOGITS
     Hop
    0.59
    Hop
    0.57
     hop
    0.57
    hop
    0.53
     Jug
    0.52
     resourceCulture
    0.51
    Jug
    0.50
     HOP
    0.49
    HOP
    0.48
    pper
    0.48
    Activations Density 1.371%

    No Known Activations