Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10324
    Prev
    Next
    INDEX
    Explanations

    references to stress and its related effects

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

    "stress" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    stress and its consequences

    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
    findpost
    -0.83
    BASEPATH
    -0.71
    ]")]
    -0.68
    OGND
    -0.67
    AMENTE
    -0.63
    zös
    -0.62
    mtable
    -0.61
    SequentialGroup
    -0.60
    etro
    -0.59
    FontOfSize
    -0.59
    POSITIVE LOGITS
     Stress
    0.81
     stress
    0.80
    stress
    0.74
     STRESS
    0.73
    Stress
    0.73
     stres
    0.73
     stresses
    0.68
     relieving
    0.63
    fully
    0.61
     Diſ
    0.59
    Activations Density 0.163%

    No Known Activations