© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5848
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific references related to medical or scientific concepts, especially pertaining to neuronal studies and drug indications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.55
    LIOT
    -0.55
     Digital
    -0.49
     digital
    -0.46
    nala
    -0.46
     connexes
    -0.45
     remb
    -0.42
    angnya
    -0.41
     its
    -0.41
    otone
    -0.41
    POSITIVE LOGITS
    новништво
    0.86
    HostException
    0.84
     laiton
    0.71
    rungsseite
    0.70
     trhu
    0.69
     AssemblyVersion
    0.69
    maketitle
    0.65
     remercier
    0.63
     chofe
    0.63
    よいよ
    0.62
    Activations Density 1.243%

    No Known Activations