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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10477
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases indicating the presence or absence of elements or conditions

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

    existence or being

    np_acts-logits-general · gemini-2.0-flash

    existence or presence

    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
    glMatrixMode
    -0.52
    MessageTagHelper
    -0.47
    AlterField
    -0.47
    躇
    -0.46
    ArrowToggle
    -0.45
    GARET
    -0.43
    AndEndTag
    -0.43
    RTLR
    -0.43
    IsMutable
    -0.43
    esz
    -0.41
    POSITIVE LOGITS
     exist
    1.80
     presence
    1.79
     exists
    1.77
     existence
    1.61
    presence
    1.55
     existed
    1.53
     Presence
    1.51
    Presence
    1.50
     aanwezig
    1.49
     présence
    1.48
    Activations Density 0.798%

    No Known Activations