© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38506
    Prev
    Next
    INDEX
    Explanations

    references to serialization processes and related classes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    serialization and deserialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     informée
    -0.53
    <
    -0.45
    ,
    -0.45
    <h2>
    -0.44
    ={<
    -0.43
    awt
    -0.43
    FileNotFound
    -0.42
    thenReturn
    -0.42
     
    -0.42
    ìm
    -0.42
    POSITIVE LOGITS
     Serializer
    1.41
    Serializer
    1.37
     serializer
    1.22
    serializer
    1.13
     serializers
    1.03
    serializers
    0.90
    erializer
    0.82
    Deserializer
    0.74
     ArrayAdapter
    0.71
    IZER
    0.71
    Activations Density 0.001%

    No Known Activations