© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    references to diapering products and their effectiveness

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

    Text after pronouns or relative pronouns such as "they", "it", or "which"

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by verb

    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
    AnimationsModule
    -0.45
     évaluation
    -0.37
     contextLoads
    -0.35
     reparación
    -0.34
     affitto
    -0.32
     vuoto
    -0.32
     preventiva
    -0.32
     kematian
    -0.31
     bezig
    -0.31
     potential
    -0.30
    POSITIVE LOGITS
    ThroughAttribute
    0.64
     snippetHide
    0.62
    Revenir
    0.59
     behaves
    0.58
     ddelweddau
    0.57
     surla
    0.57
    ConstraintMaker
    0.56
    verwijspagina
    0.55
     مشارکت‌کنندگان
    0.54
     behave
    0.54
    Activations Density 0.385%

    No Known Activations