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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11621
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and debugging statements

    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
    DockStyle
    -0.77
     pleaſure
    -0.68
     CreateTagHelper
    -0.66
     saites
    -0.65
     queſta
    -0.64
     MonoBehaviour
    -0.64
    ロウィン
    -0.63
     ſte
    -0.63
    <unused17>
    -0.62
    <unused41>
    -0.62
    POSITIVE LOGITS
    <h1>
    0.33
     Pil
    0.29
     que
    0.29
    fromnode
    0.29
     stuff
    0.28
     afirma
    0.28
    ism
    0.28
    span
    0.27
    !
    0.27
     söyl
    0.26
    Activations Density 0.145%

    No Known Activations