© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 2935
    Prev
    Next
    INDEX
    Explanations

    instances of movement or physical actions involving walking or entering spaces

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

    verbs indicating movement or physical actions related to walking and entering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     آهن
    -0.48
    TYPED
    -0.48
    обра
    -0.46
    番
    -0.45
     propa
    -0.45
    voer
    -0.43
     Prison
    -0.43
     rally
    -0.43
     TimeUnit
    -0.43
    iset
    -0.42
    POSITIVE LOGITS
    Personendaten
    1.03
    rungsseite
    0.94
    RectangleBorder
    0.93
    ResponseWriter
    0.91
    fjspx
    0.89
    MLLoader
    0.89
    elemField
    0.82
    BeginInit
    0.81
    IntoConstraints
    0.81
     createSprite
    0.80
    Activations Density 0.117%

    No Known Activations