© 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. 25-GEMMASCOPE-RES-16K
    11. 2315
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals and their professional expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mfg
    -0.68
    Roblox
    -0.65
     aggressiveness
    -0.65
    UFACT
    -0.61
    存于互联网档案馆
    -0.59
    clerview
    -0.58
    плуата
    -0.58
    StateList
    -0.58
    👔
    -0.58
     bekämp
    -0.58
    POSITIVE LOGITS
     facilitation
    0.72
     sacred
    0.72
     facilitators
    0.71
     deepening
    0.70
    Sacred
    0.70
     healing
    0.70
     nourishing
    0.70
     facilitator
    0.70
     Sacred
    0.69
     somatic
    0.69
    Activations Density 0.535%

    No Known Activations