© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2085
    Prev
    Next
    INDEX
    Explanations

    grammatical structures related to the present tense in singular form

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

    grammatical structures and syntactic parsing elements like verb phrases, noun phrases, and tense markers.

    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
     DAF
    -0.35
     كومونز
    -0.34
    fillType
    -0.33
    EndContext
    -0.32
    zzled
    -0.32
    WithError
    -0.32
     viciss
    -0.32
     illi
    -0.32
    DOCTYPE
    -0.32
     Symb
    -0.32
    POSITIVE LOGITS
     tense
    0.91
     tenses
    0.82
     past
    0.79
     Tense
    0.79
     Past
    0.78
    Past
    0.73
     PAST
    0.70
     Present
    0.70
     third
    0.67
    past
    0.64
    Activations Density 0.113%

    No Known Activations