© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3771
    Prev
    Next
    INDEX
    Explanations

    themes related to zombies and post-apocalyptic scenarios

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

    Apocalyptic or survival themes

    np_acts-logits-general · gemini-2.0-flash

    zombie survival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phép
    -0.46
    bindings
    -0.46
    ônimo
    -0.45
    gebras
    -0.45
     büy
    -0.44
    etton
    -0.43
    thansa
    -0.43
     مُعرِّف
    -0.43
    bka
    -0.43
     calum
    -0.42
    POSITIVE LOGITS
     survivors
    1.51
     survival
    1.50
     survivor
    1.44
     Survival
    1.36
    survival
    1.35
    survi
    1.34
     Survivors
    1.31
    Survival
    1.26
     SURV
    1.24
     survi
    1.24
    Activations Density 0.138%

    No Known Activations