Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5261
    Prev
    Next
    INDEX
    Explanations

    instructions related to mechanical assembly and maintenance

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

    Disassembly, removal, or replacement of parts

    np_acts-logits-general · gemini-2.0-flash

    taking apart components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SuspendLayout
    -0.64
     fulfilment
    -0.60
     terecht
    -0.59
     utafitiHapana
    -0.57
    BeginInit
    -0.56
     gynhyrchwyd
    -0.55
    KommentareTeilen
    -0.55
     erfüllt
    -0.54
     ratification
    -0.54
    RegistryLite
    -0.54
    POSITIVE LOGITS
     disassemble
    1.04
     disassembly
    1.00
     disassembled
    0.93
     remove
    0.88
     replacing
    0.86
     replacement
    0.86
     removal
    0.85
     removing
    0.85
     replace
    0.85
     inspect
    0.84
    Activations Density 0.174%

    No Known Activations