© 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. 31-GEMMASCOPE-RES-16K
    11. 7000
    Prev
    Next
    INDEX
    Explanations

    assertions regarding the nature or quality of something

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

    contractions with "it" followed by a form of "to be" (it's, it is).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erreferentziak
    -0.56
    SourceChecksum
    -0.39
    writerow
    -0.35
    MENAFN
    -0.34
    AndEndTag
    -0.33
    OfWork
    -0.33
     फै
    -0.32
    ParallelGroup
    -0.31
     durar
    -0.31
     flows
    -0.31
    POSITIVE LOGITS
     advantageous
    0.64
    UnusedPrivate
    0.62
     wise
    0.62
     prudent
    0.57
    Personensuche
    0.56
     beneficial
    0.56
     imperative
    0.56
    ftagPool
    0.55
     wireType
    0.55
     possible
    0.54
    Activations Density 0.260%

    No Known Activations