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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10346
    Prev
    Next
    INDEX
    Explanations

    class and method-related elements in programming code

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

    Code snippets containing "this" and punctuation

    np_acts-logits-general · gemini-2.0-flash

    this followed by punctuation

    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
     MainAxisSize
    -0.88
     autorytatywna
    -0.84
    SequentialGroup
    -0.84
    AddTagHelper
    -0.81
     Савезне
    -0.80
     ExecuteAsync
    -0.80
    ParallelGroup
    -0.77
    BufferException
    -0.74
    offsetof
    -0.73
     @"/
    -0.73
    POSITIVE LOGITS
    apha
    0.52
     godk
    0.49
     cópia
    0.48
     œuvres
    0.47
     communs
    0.47
     juridiques
    0.44
     scolaires
    0.44
     démocr
    0.44
     supérieures
    0.43
     reproducción
    0.43
    Activations Density 0.208%

    No Known Activations