© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8230
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to serialization and deserialization processes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sune
    -0.47
    openqa
    -0.47
    CodeAttribute
    -0.46
    CreateIndex
    -0.46
    IndexOutOfBounds
    -0.45
     sbag
    -0.45
     tkinter
    -0.44
    ähteet
    -0.44
     kentang
    -0.44
     trouverez
    -0.44
    POSITIVE LOGITS
     serialization
    1.25
     serialized
    1.16
    序列化
    1.11
     serialize
    1.10
     serial
    1.08
     Serial
    1.04
    serial
    1.03
    Serialize
    0.97
    Serializer
    0.97
    Serial
    0.96
    Activations Density 0.611%

    No Known Activations