© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5992
    Prev
    Next
    INDEX
    Explanations

    instances of the word "inspire" or its variations, indicating a focus on motivation and influence

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

    Texts containing "inspired" or "inspire"

    np_acts-logits-general · gemini-2.0-flash

    inspire and be inspired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.60
    npmjs
    -0.56
    mfenced
    -0.49
    üne
    -0.49
    y
    -0.48
    nativeElement
    -0.46
    ी
    -0.46
    classNames
    -0.46
    acea
    -0.46
    oplan
    -0.45
    POSITIVE LOGITS
     Motiv
    0.93
     motivates
    0.93
     pinulongan
    0.92
    Motiv
    0.91
     Motivation
    0.89
     motivation
    0.88
     motivate
    0.88
     motivated
    0.86
     motivations
    0.85
     inspires
    0.84
    Activations Density 0.229%

    No Known Activations