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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13411
    Prev
    Next
    INDEX
    Explanations

    references to stack traces and related technical terms

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

    "Stack" or "StackExchange"

    np_acts-logits-general · gemini-2.0-flash

    stack trace or stack overflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.72
    новниш
    -0.63
    publique
    -0.63
    SpringBootTest
    -0.57
    InteropServices
    -0.57
    WriteTagHelper
    -0.57
    AssignableFrom
    -0.57
    CORBA
    -0.56
    **/
    -0.56
    @[+][
    -0.56
    POSITIVE LOGITS
     stack
    1.57
     stacks
    1.53
     Stack
    1.47
     Stacks
    1.38
     STACK
    1.36
    Stack
    1.29
    stack
    1.25
    STACK
    1.23
     pile
    1.17
    stacks
    1.13
    Activations Density 0.169%

    No Known Activations