© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7517
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to relaxation and calming experiences

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

    feeling calm

    np_acts-logits-general · gemini-2.0-flash

    state of relaxed

    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
    دانشنامهٔ
    -0.67
    ReusableCell
    -0.57
    RunWith
    -0.55
     NSCoder
    -0.51
     estekak
    -0.51
    VersionUID
    -0.51
     Normdatei
    -0.50
     ब्रेकडाउन
    -0.48
    RenderAtEndOf
    -0.48
    antMatchers
    -0.47
    POSITIVE LOGITS
     relax
    1.96
    Relax
    1.89
     relaxed
    1.84
     Relax
    1.81
    relax
    1.80
     relaxes
    1.68
     relaxing
    1.68
     relaxation
    1.66
    relaxed
    1.66
     Relaxed
    1.63
    Activations Density 0.127%

    No Known Activations