© 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. 2-GEMMASCOPE-RES-16K
    6. 5182
    Prev
    Next
    INDEX
    Explanations

    iterations of protocol structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.73
    UnknownFields
    -0.69
    makeConstraints
    -0.68
    pecia
    -0.65
     CommonModule
    -0.63
     trovo
    -0.62
    SuppressLint
    -0.62
     >=",
    -0.61
     Tark
    -0.61
     hiss
    -0.61
    POSITIVE LOGITS
    proto
    3.39
     proto
    3.26
    Proto
    3.13
     Proto
    3.11
     PROTO
    2.45
    PROTO
    2.30
     prototype
    2.27
     prototypes
    2.22
     Prototype
    2.04
    Prototype
    1.94
    Activations Density 0.064%

    No Known Activations