© 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. 31-GEMMASCOPE-RES-16K
    11. 12598
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

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

    the phrase "at the" followed by a temporal reference word (like "time", "same", "beginning", "end").

    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
     گزارش
    -0.42
     محفوظة
    -0.40
     ModelRenderer
    -0.40
     المعيارى
    -0.37
     tré
    -0.36
     AUTHORITIES
    -0.36
    Priv
    -0.36
     Administrativna
    -0.36
    esModule
    -0.36
     szóci
    -0.36
    POSITIVE LOGITS
     outset
    0.73
     forefront
    0.68
     expense
    0.64
     least
    0.62
     discretion
    0.59
    󠁿
    0.55
     urging
    0.55
     juncture
    0.54
     request
    0.54
     mercy
    0.51
    Activations Density 0.110%

    No Known Activations