© 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. 420
    Prev
    Next
    INDEX
    Explanations

    elements related to JavaScript modules and function declarations in a coding context

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

    Code snippets with parameters, regions, or indices

    np_acts-logits-general · gemini-2.0-flash

    configuration structure keywords

    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
    <eos>
    -0.88
    .
    -0.75
    ↵↵
    -0.71
     
    -0.59
    ↵
    -0.53
    。
    -0.53
     "/";
    -0.51
    ).
    -0.50
     the
    -0.50
     .
    -0.50
    POSITIVE LOGITS
     autorytatywna
    1.25
    bootstrapcdn
    0.89
    :
    0.86
     kasarigan
    0.86
     propOrder
    0.85
    :✨
    0.85
     itſelf
    0.84
    principalColumn
    0.82
    énario
    0.81
    MemoryWarning
    0.81
    Activations Density 0.385%

    No Known Activations