© 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. 24-GEMMASCOPE-RES-16K
    11. 7873
    Prev
    Next
    INDEX
    Explanations

    programming and data structure elements in code, particularly focusing on variable declarations and function definitions

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

    Code snippets with parentheses/brackets

    np_acts-logits-general · gemini-2.0-flash

    programmatic code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "){
    -0.61
    '){
    -0.59
    NewUrlParser
    -0.55
    ])
    -0.54
     rând
    -0.54
     tár
    -0.53
    .)}
    -0.53
    '){
    -0.53
     fallu
    -0.51
    '])
    -0.51
    POSITIVE LOGITS
    )+
    0.80
    )+"
    0.62
    )-
    0.60
     onOptions
    0.56
    )/
    0.56
    httphttps
    0.56
    WithMany
    0.55
    openConnection
    0.55
    Caprio
    0.54
    )+(
    0.54
    Activations Density 0.373%

    No Known Activations