© 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 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. 10013
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and hypothetical situations

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

    Follows "in which" or similar phrasing

    np_acts-logits-general · gemini-2.0-flash

    in which case

    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
    OGND
    -0.46
     propOrder
    -0.38
    出版年
    -0.36
     sahiptir
    -0.36
    IntoConstraints
    -0.35
     Ludlow
    -0.33
    golang
    -0.33
    PropertyGroup
    -0.32
    GEBURTS
    -0.32
     doInBackground
    -0.32
    POSITIVE LOGITS
     then
    1.69
     тогда
    1.56
     wtedy
    1.52
     entonces
    1.48
     allora
    1.46
    Тогда
    1.38
     Тогда
    1.33
    then
    1.29
     Then
    1.27
    ówczas
    1.27
    Activations Density 0.933%

    No Known Activations