© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14727
    Prev
    Next
    INDEX
    Explanations

    assert statements, particularly those checking for non-null conditions and invariants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    SPATH
    -0.53
    RenderAtEndOf
    -0.49
    +#+#
    -0.46
    PickerController
    -0.44
    minecraftforge
    -0.40
     tolua
    -0.40
     InputDecoration
    -0.40
    SCA
    -0.40
    {(-
    -0.39
    ceptibility
    -0.39
    POSITIVE LOGITS
    cassert
    0.57
    setVerticalGroup
    0.54
    assert
    0.49
    ंदीखरीदारी
    0.47
    assertNotNull
    0.47
    ASSERT
    0.46
     perfección
    0.42
    StateException
    0.40
    posedge
    0.40
    JspWriter
    0.38
    Activations Density 0.108%

    No Known Activations