© 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 EvalsExportsinterp-engineNEWAPI 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. 12814
    Prev
    Next
    INDEX
    Explanations

    phrases indicating persistence or continuity

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

    Sentences containing the word "remain[s]"

    np_acts-logits-general · gemini-2.0-flash

    state of being remains

    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
     ſy
    -0.78
     ſche
    -0.76
     ſch
    -0.73
     ſever
    -0.65
     Inſ
    -0.65
     juſ
    -0.65
     pleaſure
    -0.64
     Anſ
    -0.63
     courseId
    -0.60
     ſte
    -0.59
    POSITIVE LOGITS
     remains
    1.63
     remain
    1.61
     remained
    1.45
    remain
    1.42
    remains
    1.40
     Remain
    1.39
     Remains
    1.37
    Remain
    1.31
     rimane
    1.09
     permanece
    1.05
    Activations Density 0.153%

    No Known Activations