© 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. 2-GEMMASCOPE-RES-16K
    6. 9116
    Prev
    Next
    INDEX
    Explanations

    phrases related to stepping or movement actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvrt
    -0.53
    dry
    -0.47
    LLOW
    -0.45
     dry
    -0.45
    Dry
    -0.45
     speculative
    -0.44
     developed
    -0.43
    punkten
    -0.43
     personne
    -0.43
    splitlines
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    1.11
    makeConstraints
    0.99
     мәкал
    0.92
    migrationBuilder
    0.89
     Roskov
    0.88
    XmlAccessType
    0.88
     IndexPath
    0.86
     StatefulWidget
    0.84
     Administrativna
    0.82
    TintMode
    0.82
    Activations Density 0.113%

    No Known Activations