© 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. 28-GEMMASCOPE-RES-16K
    11. 7942
    Prev
    Next
    INDEX
    Explanations

    programming functions and method calls related to testing and checking conditions

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

    Code related to conditional checks

    np_acts-logits-general · gemini-2.0-flash

    checking or testing conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.48
     GenerationType
    -0.46
     Chwiliwch
    -0.45
    printStackTrace
    -0.44
    makeText
    -0.43
    bootstrapcdn
    -0.42
    RTSC
    -0.41
    DockStyle
    -0.39
     TextInputType
    -0.39
    FieldBuilder
    -0.38
    POSITIVE LOGITS
     check
    1.23
     checks
    1.21
     checking
    1.16
     Checks
    1.09
    check
    1.07
     Check
    1.07
     whether
    1.02
    Check
    1.01
     Checking
    1.00
    checking
    0.98
    Activations Density 0.843%

    No Known Activations