© 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. 1984
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and phrases, particularly those that indicate programming functions, options, and commands

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

    before abbreviated variable names

    np_acts-logits-general · gemini-2.0-flash

    levels of currency or code

    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
    RegressionTest
    -0.61
    stdio
    -0.61
    ParallelGroup
    -0.61
    AndroidJUnit
    -0.58
    IsMutable
    -0.58
    著
    -0.56
    StatusOK
    -0.55
    着
    -0.54
     pleaſure
    -0.54
    大了
    -0.54
    POSITIVE LOGITS
    cipar
    0.49
    ificar
    0.49
    brar
    0.49
    bear
    0.48
    FieldBuilder
    0.47
    gdx
    0.46
     Yar
    0.46
    carlos
    0.45
    tuar
    0.45
    ształ
    0.45
    Activations Density 0.065%

    No Known Activations