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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122852
    Prev
    Next
    INDEX
    Explanations

    occurrences of periods or full stops in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     يتيمه
    -0.76
     kasarigan
    -0.66
    unknownFields
    -0.58
    RTSC
    -0.57
     pinulongan
    -0.57
    脚注の使い方
    -0.54
    KURZBESCHREIBUNG
    -0.53
    TemporalType
    -0.52
     contextLoads
    -0.49
    ագրություններ
    -0.48
    POSITIVE LOGITS
    <bos>
    0.45
     website
    0.44
    határoz
    0.42
     canteen
    0.40
    你要
    0.39
     Jalan
    0.39
    EndProject
    0.39
    reden
    0.39
    談社
    0.38
    antMatchers
    0.38
    Activations Density 0.004%

    No Known Activations