© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1201
    Prev
    Next
    INDEX
    Explanations

    themes related to transformation and impact on lives

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

    "change lives" or variations of the phrase

    np_acts-logits-general · gemini-2.0-flash

    life-changing events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},
    -0.60
    (""));
    -0.59
    IntoConstraints
    -0.58
    $")
    -0.53
    digkeit
    -0.52
     Paglinawan
    -0.51
    */;
    -0.49
    ørs
    -0.48
    '],'
    -0.48
     edge
    -0.48
    POSITIVE LOGITS
     lives
    1.82
     Lives
    1.42
     life
    1.38
     LIVES
    1.32
    lives
    1.31
     vidas
    1.28
    life
    1.18
    Lives
    1.18
     Life
    1.16
     lifes
    1.16
    Activations Density 0.132%

    No Known Activations