© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8468
    Prev
    Next
    INDEX
    Explanations

    conditional statements and assertions in programming code

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

    Code that contains length, size, timeout, or index variables

    np_acts-logits-general · gemini-2.0-flash

    not equal, non-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.80
    featureID
    -0.80
    enterOuterAlt
    -0.75
    sizeCache
    -0.71
    KommentareTeilen
    -0.70
    MessageTagHelper
    -0.69
    principalTable
    -0.67
    AutoScaleMode
    -0.67
    RegressionTest
    -0.67
    mybatisplus
    -0.66
    POSITIVE LOGITS
     nonzero
    1.36
     non
    1.21
    non
    1.13
    Non
    1.12
     Non
    1.10
    nonzero
    1.02
     !=
    0.99
    非
    0.96
     ≠
    0.93
     NON
    0.93
    Activations Density 0.501%

    No Known Activations