© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    programming language structures, particularly related to constructors and definitions

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

    Haskell code related to DLMLifecyclePolicySchedule

    np_acts-logits-general · gemini-2.0-flash

    haskell lenses

    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
    Itz
    -0.46
     <=",
    -0.45
     Irish
    -0.44
    장
    -0.44
    shaded
    -0.41
    込んで
    -0.41
    Ké
    -0.41
     mes
    -0.41
     pog
    -0.40
    OpCode
    -0.40
    POSITIVE LOGITS
     Inverness
    0.82
     Leith
    0.79
    الحياه
    0.79
    OGND
    0.75
    AntiForgeryToken
    0.73
     Edinburgh
    0.73
     Aberdeen
    0.70
     Scots
    0.70
     MacLeod
    0.69
    Aberdeen
    0.69
    Activations Density 0.185%

    No Known Activations