© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function definitions and method calls in programming languages

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

    Code syntax involving parentheses and colons

    np_acts-logits-general · gemini-2.0-flash

    code structures and types

    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
     "
    -0.49
     l
    -0.46
    QWidget
    -0.45
     EventArgs
    -0.43
    l
    -0.42
     lo
    -0.42
     ob
    -0.42
     stuff
    -0.41
     qui
    -0.41
    ItemSelected
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.11
     quæ
    0.98
     AssemblyTitle
    0.96
     habet
    0.89
    GEBURTSDATUM
    0.89
     purpoſe
    0.88
     auroit
    0.88
     plufieurs
    0.87
     Monfieur
    0.87
     poffible
    0.86
    Activations Density 0.110%

    No Known Activations