© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3085
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate future actions or plans

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

    "Gonna" or "gotta" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    gonna / going to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geografic
    -0.38
    ようになりました
    -0.38
     traced
    -0.38
    的她
    -0.37
     gynhyrchwyd
    -0.37
     lähe
    -0.37
     nedir
    -0.36
     traces
    -0.36
    彼女
    -0.36
     laaj
    -0.35
    POSITIVE LOGITS
    gonna
    1.07
    Gonna
    1.07
     gonna
    1.02
     Gonna
    0.98
     GONNA
    0.93
    gotta
    0.62
     gotta
    0.60
     Gotta
    0.57
    Gotta
    0.57
    gon
    0.57
    Activations Density 0.099%

    No Known Activations